© 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. 177641
    Prev
    Next
    INDEX
    Explanations

    choice and selection

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

    roleplaying harmful scenarios

    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
    .
    0.49
     springtime
    0.47
    ので
    0.46
     を
    0.44
     イ
    0.44
    裡
    0.44
    よりも
    0.43
     その
    0.43
    க்குப்
    0.43
     ニ
    0.42
    POSITIVE LOGITS
    artists
    0.45
    设计的
    0.45
    Articulation
    0.44
    יל
    0.43
    ून
    0.42
     Mortality
    0.42
    濩
    0.42
     선택
    0.41
    డ్‌
    0.41
    Monty
    0.41
    Activations Density 0.000%

    No Known Activations