© 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. 17122
    Prev
    Next
    INDEX
    Explanations

    going and

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

    security and cost

    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
    UH
    0.46
    Ⅽ
    0.46
     liberated
    0.45
    <unused2164>
    0.44
     partitioned
    0.44
     поді
    0.44
    یک
    0.44
    ப்பட்டுள்ளது
    0.44
     acorns
    0.44
     হইয়৷
    0.43
    POSITIVE LOGITS
     soutien
    0.46
     Doris
    0.46
    erver
    0.45
    你应该
    0.44
    高志森
    0.44
    pean
    0.44
     UserDefaults
    0.43
     vad
    0.43
     Erz
    0.43
     User
    0.43
    Activations Density 0.000%

    No Known Activations