© 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. 22644
    Prev
    Next
    INDEX
    Explanations

    value antiques

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

    secrets and birthday parties

    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
     ಆದ್ದರಿಂದ
    0.47
     Robbins
    0.46
     bolj
    0.46
     காட்ட
    0.46
     परिचय
    0.44
     អ
    0.43
    採取
    0.43
    songs
    0.43
    singer
    0.43
    paro
    0.42
    POSITIVE LOGITS
    เภ
    0.54
    ان
    0.52
     sash
    0.50
     trit
    0.49
     superst
    0.48
     antiques
    0.47
    剡
    0.46
     value
    0.46
    ٹی
    0.46
    値を
    0.45
    Activations Density 0.000%

    No Known Activations