© 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-16K
    7. 12964
    Prev
    Next
    INDEX
    Explanations

    sent to recipients or destinations

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

    delivering to recipient

    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_16k_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
     എന്ത
    0.50
     निघा
    0.47
    arakhand
    0.43
     മാര്‍
    0.41
     ร่วม
    0.41
    伷
    0.41
     स्वतंत्र
    0.40
    ҹ
    0.40
    ചര്യ
    0.40
     കൂ
    0.40
    POSITIVE LOGITS
     via
    0.83
     VIA
    0.66
    via
    0.64
     into
    0.60
     Via
    0.59
     vía
    0.59
    into
    0.56
     onto
    0.55
    Via
    0.55
     recipient
    0.55
    Activations Density 0.434%

    No Known Activations