© 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. 88041
    Prev
    Next
    INDEX
    Explanations

    organizations, companies, excessive

    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
    ['
    0.42
    Ῥ
    0.40
    Joke
    0.40
    ેશ
    0.39
    ['_
    0.38
    dist
    0.38
    Joy
    0.38
    <0xA8>
    0.38
     ['
    0.37
    sponge
    0.37
    POSITIVE LOGITS
     déta
    0.53
     lalu
    0.49
    olina
    0.48
    etta
    0.47
     factores
    0.46
     nécessaire
    0.46
     utilisée
    0.45
     necesitar
    0.45
     milik
    0.45
    する必要
    0.45
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.