© 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. 146493
    Prev
    Next
    INDEX
    Explanations

    centre of the greatest

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

    yellow becomes

    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
    E
    0.55
    A
    0.53
    EW
    0.52
    S
    0.50
    Eg
    0.48
    D
    0.48
    Ef
    0.46
    R
    0.46
    EH
    0.46
    Rah
    0.45
    POSITIVE LOGITS
    移動
    0.50
     maximising
    0.49
     promulgating
    0.48
     почти
    0.47
    britannien
    0.46
    間に
    0.46
     অবশেষে
    0.45
    実に
    0.44
    間で
    0.44
     дви
    0.44
    Activations Density 0.001%

    No Known Activations