© 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. 212946
    Prev
    Next
    INDEX
    Explanations

    codes and data

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

    hypothetical scenarios and choices

    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
     모르
    0.61
     фаразлау
    0.57
    𒌨
    0.57
     言っ
    0.54
     أف
    0.54
     식으로
    0.54
     भाजी
    0.54
    ˀ
    0.54
    ᴬ
    0.53
     ख़ु
    0.52
    POSITIVE LOGITS
    <start_of_image>
    0.44
     counties
    0.43
     network
    0.43
    多家
    0.42
    -
    0.42
     cyclical
    0.42
    cyclic
    0.41
    tags
    0.40
    schools
    0.40
    /
    0.40
    Activations Density 0.000%

    No Known Activations