© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11929
    Prev
    Next
    INDEX
    Explanations

    sections or list items

    np_acts-logits-general · gemini-2.5-flash-lite

    headings with why or numbers

    np_acts-logits-general · gemini-2.5-flash-lite

    formatted text sections

    np_max-act · claude-4-5-sonnetTriggered by @sk5695

    structured document formatting

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     পছন্দের
    0.51
    数の
    0.50
    そして
    0.50
    യുടെ
    0.46
    來的
    0.46
     navegar
    0.46
    他
    0.45
    然後
    0.44
     중심
    0.44
    اگر
    0.44
    POSITIVE LOGITS
    v
    0.50
    ard
    0.48
    e
    0.47
    ί
    0.47
    ne
    0.46
     Type
    0.46
    έ
    0.46
    ждение
    0.46
    ιστή
    0.45
     Facts
    0.45
    Activations Density 0.004%

    No Known Activations