© 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. 13386
    Prev
    Next
    INDEX
    Explanations

    from to ranges

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

    from [start] to [end]

    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
    <unused2>
    0.49
    μου
    0.48
     масло
    0.48
    ায়
    0.47
    lardı
    0.46
    thisobject
    0.46
     paylaş
    0.46
    appliqu
    0.46
     крово
    0.45
     camadas
    0.45
    POSITIVE LOGITS
    0.54
     low
    0.49
     Range
    0.47
     #
    0.47
     >=
    0.46
     range
    0.46
     conservative
    0.45
     UK
    0.45
     extremely
    0.45
     European
    0.44
    Activations Density 0.000%

    No Known Activations