© 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. 9781
    Prev
    Next
    INDEX
    Explanations

    end of common phrases

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

    common phrases

    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
    :
    0.45
    ization
    0.44
     말미암아
    0.42
     corpses
    0.41
    NOWLEDGE
    0.41
    usages
    0.41
    consciousness
    0.41
     np
    0.40
    眽
    0.39
    IZATION
    0.38
    POSITIVE LOGITS
    <unused2169>
    0.47
    𒐪
    0.43
    öy
    0.43
    ла
    0.42
     odlič
    0.42
    ifício
    0.42
    可谓
    0.42
     tiež
    0.41
     família
    0.41
    ěl
    0.41
    Activations Density 0.171%

    No Known Activations