© 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-262K
    7. 181537
    Prev
    Next
    INDEX
    Explanations

    choices or LMS

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

    using other websites or SVB

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     or
    0.54
     aber
    0.54
     out
    0.52
     Turin
    0.52
    _
    0.52
     Sides
    0.50
     which
    0.50
     slaughter
    0.49
     Fallout
    0.48
     Puritan
    0.48
    POSITIVE LOGITS
    更有
    0.46
    ádza
    0.46
    ándo
    0.44
    っしゃ
    0.44
    pdbonly
    0.44
    悰
    0.44
    سين
    0.43
    ciencia
    0.42
    onio
    0.42
    clientY
    0.42
    Activations Density 0.001%

    No Known Activations