© 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. 97089
    Prev
    Next
    INDEX
    Explanations

    shared equally, pen to, fee will, favor to, free billing

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

    foreign languages and concepts

    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
     –
    0.48
     Playoffs
    0.48
     kell
    0.47
     -
    0.46
    binder
    0.45
     mar
    0.45
     whis
    0.44
     requires
    0.43
     우
    0.43
     חי
    0.43
    POSITIVE LOGITS
    ாங்க
    0.59
    atributo
    0.56
    стран
    0.53
     காணலாம்
    0.51
    ieurs
    0.50
    Ἥ
    0.50
    lichting
    0.49
    народ
    0.49
     allemaal
    0.49
    времен
    0.49
    Activations Density 0.001%

    No Known Activations