© 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. 131992
    Prev
    Next
    INDEX
    Explanations

    programming constructs

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

    programming language keywords

    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
    3
    0.58
    5
    0.53
    ៥
    0.52
    uwe
    0.47
    side
    0.47
    шена
    0.46
     અથવા
    0.44
    RS
    0.44
    াঃ
    0.44
    4
    0.43
    POSITIVE LOGITS
     मिलने
    0.45
     interruptions
    0.43
    štění
    0.43
    ंदी
    0.43
    ფორმა
    0.42
    ِح
    0.42
     imati
    0.42
    लेला
    0.42
     företag
    0.40
    দিনের
    0.40
    Activations Density 0.002%

    No Known Activations