© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 82395
    Prev
    Next
    INDEX
    Explanations

    obscenity and fermentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    น
    0.54
    н
    0.51
    (((
    0.47
    {
    0.45
    ↵
    0.45
    ((
    0.45
     cigarette
    0.44
    ﯼ
    0.44
    弼
    0.44
    ייה
    0.42
    POSITIVE LOGITS
     antennis
    0.48
     vaso
    0.45
     ယ
    0.44
     سوم
    0.44
     principales
    0.44
     робо
    0.43
     அணுக
    0.43
     التق
    0.42
    ائص
    0.42
     විශ්
    0.42
    Activations Density 0.010%

    No Known Activations