© 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. 73950
    Prev
    Next
    INDEX
    Explanations

    dates and times

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

    technical status reports

    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
     AMOUNT
    0.46
    বারি
    0.45
    ទេ
    0.44
    足球
    0.43
    東北
    0.43
    壩
    0.42
     형식
    0.42
    坡
    0.41
     純
    0.40
    樹
    0.40
    POSITIVE LOGITS
     delays
    0.52
     délais
    0.48
     fontes
    0.46
     временем
    0.46
     anderen
    0.45
     momentum
    0.44
     calming
    0.44
     Firmware
    0.44
     дополнительных
    0.44
     occasionally
    0.44
    Activations Density 0.000%

    No Known Activations