© 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. 27626
    Prev
    Next
    INDEX
    Explanations

    followed by specific phrases

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

    ideas, discoveries, and decisions

    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
     dell
    0.53
     নিজেরাই
    0.46
     A
    0.46
     battle
    0.46
     Guerra
    0.46
     Lugar
    0.46
    version
    0.45
     G
    0.45
     gel
    0.45
     bull
    0.45
    POSITIVE LOGITS
    Droite
    0.54
    鲷
    0.47
    ີ້
    0.46
    cemment
    0.46
    াদে
    0.46
     interceptions
    0.46
    ті
    0.46
     émer
    0.45
    Marne
    0.45
     hés
    0.45
    Activations Density 0.000%

    No Known Activations