© 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. 135087
    Prev
    Next
    INDEX
    Explanations

    article above

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

    harmful or conversational content

    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
    나
    0.49
     quantifier
    0.49
     near
    0.45
     and
    0.45
    টা
    0.45
    نا
    0.44
     userRouter
    0.44
     hinting
    0.44
     informing
    0.44
     ي
    0.43
    POSITIVE LOGITS
     वार्षिक
    0.52
    hobby
    0.50
    annual
    0.49
    institutional
    0.44
    bollywood
    0.44
    awards
    0.44
    twenty
    0.43
    चालित
    0.43
     বৎসরের
    0.42
    unfinished
    0.41
    Activations Density 0.004%

    No Known Activations