© 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. 58611
    Prev
    Next
    INDEX
    Explanations

    conditions and transfer

    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
    引き続き
    0.50
    ப்போ
    0.47
    =\
    0.46
    ان
    0.46
     పూ
    0.45
    Argonne
    0.44
    でした
    0.43
     Andi
    0.43
    ப்புக
    0.41
    یوں
    0.41
    POSITIVE LOGITS
    getStringExtra
    0.48
     felicidade
    0.46
     dahulu
    0.46
     ferv
    0.44
     便
    0.44
     জীবনী
    0.43
     felicidad
    0.43
    chedule
    0.43
    拼接
    0.41
     dormitory
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.