© 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. 99114
    Prev
    Next
    INDEX
    Explanations

    bubble popping, eye chart

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

    punctuations or connectors like and, is

    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
    在
    0.46
    cap
    0.46
    Capability
    0.46
    LC
    0.45
    Gre
    0.45
    Luc
    0.44
    Compound
    0.43
    Cap
    0.42
    Cite
    0.42
    @
    0.41
    POSITIVE LOGITS
     જાહેર
    0.55
    렸
    0.51
    म्मू
    0.51
    两个人
    0.50
    䀠
    0.50
    圴
    0.50
    ⚉
    0.49
     выпу
    0.48
    ணும்
    0.48
    篒
    0.48
    Activations Density 0.000%

    No Known Activations