© 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. 196804
    Prev
    Next
    INDEX
    Explanations

    common phrases or specific names

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

    `depending on`

    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
    罠
    0.58
    iflower
    0.48
    墾
    0.48
    гент
    0.47
    моби
    0.46
    आपके
    0.46
    ств
    0.46
    дый
    0.45
    луйста
    0.45
    農業
    0.45
    POSITIVE LOGITS
     året
    0.55
     –
    0.55
     wholeheartedly
    0.52
    น
    0.48
     enthusi
    0.47
     celebrates
    0.47
     became
    0.46
     announced
    0.46
     edition
    0.46
     spekt
    0.46
    Activations Density 0.000%

    No Known Activations