© 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. 101203
    Prev
    Next
    INDEX
    Explanations

    Ten Meritorious Acts

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

    explain culminating maximum intercept cover

    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
    Carry
    0.52
    櫸
    0.49
    𝓈
    0.48
    スポ
    0.48
    写真を
    0.48
    POLY
    0.47
    禇
    0.47
    致
    0.47
     homogé
    0.46
    carried
    0.45
    POSITIVE LOGITS
     murmur
    0.54
     Kent
    0.53
     Qui
    0.52
     War
    0.49
     Wizard
    0.49
    ?
    0.48
    uming
    0.47
     Variant
    0.47
     panic
    0.47
     Wall
    0.47
    Activations Density 0.000%

    No Known Activations