© 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. 104731
    Prev
    Next
    INDEX
    Explanations

    United Kingdom, states, Mommy Group

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

    positional phrases or conjunctions

    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
    or
    0.47
    are
    0.47
     as
    0.44
    off
    0.43
     or
    0.43
    a
    0.43
    age
    0.42
    aps
    0.42
    incor
    0.40
     Avant
    0.40
    POSITIVE LOGITS
    莯
    0.49
     দার্শন
    0.48
    䟝
    0.48
    čio
    0.47
     θέση
    0.47
    靶
    0.46
     nasa
    0.46
     COUNCIL
    0.45
     tím
    0.45
    ígen
    0.45
    Activations Density 0.001%

    No Known Activations