© 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. 91387
    Prev
    Next
    INDEX
    Explanations

    approximate days

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

    building specific things

    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
     Č
    0.45
     sábado
    0.43
     Boc
    0.43
     midwives
    0.43
     സംസാ
    0.42
     Lesotho
    0.41
     শুক্র
    0.41
    ivac
    0.41
     jueves
    0.41
     specialising
    0.41
    POSITIVE LOGITS
    Data
    0.49
    tais
    0.46
    ་
    0.43
    Finished
    0.43
    กฏ
    0.43
    Datas
    0.43
     уте
    0.42
    Disable
    0.42
    Chips
    0.42
    ือ
    0.42
    Activations Density 0.000%

    No Known Activations