© 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. 199649
    Prev
    Next
    INDEX
    Explanations

    children talking away

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

    new material alternatives

    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
     个
    0.52
    称
    0.50
     நோக்கி
    0.49
    𒐪
    0.48
    wa
    0.46
    proximity
    0.46
    感到
    0.45
    resu
    0.45
     发布
    0.45
     低
    0.45
    POSITIVE LOGITS
     Italians
    0.50
     intrusions
    0.48
     multinationals
    0.48
     exclusives
    0.47
     corporates
    0.46
    랍
    0.46
     appraisals
    0.45
     atrocities
    0.44
     internationaux
    0.44
    럴
    0.44
    Activations Density 0.000%

    No Known Activations