© 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. 177808
    Prev
    Next
    INDEX
    Explanations

    Director, consent, landlords

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

    combining averaging integrating mirroring

    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
     và
    0.71
     और
    0.63
     και
    0.60
     และ
    0.58
     и
    0.57
     καὶ
    0.57
     এবং
    0.55
     و
    0.54
     અને
    0.54
     आणि
    0.54
    POSITIVE LOGITS
    estructura
    0.55
     privilégi
    0.50
    composed
    0.49
    approche
    0.47
    フォロー
    0.46
    creation
    0.46
    penet
    0.45
    ਟੀ
    0.45
    intentional
    0.45
    複製
    0.44
    Activations Density 0.000%

    No Known Activations