© 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. 75226
    Prev
    Next
    INDEX
    Explanations

    contraindicated limitations

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

    house on sand metaphor

    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
    Z
    0.69
    z
    0.61
    Y
    0.59
    u
    0.58
    V
    0.57
    F
    0.55
    Dubai
    0.55
    VQ
    0.55
    in
    0.54
    B
    0.54
    POSITIVE LOGITS
     ettha
    0.58
     basilaires
    0.54
    螌
    0.52
     Dessous
    0.50
     natthi
    0.50
     yattha
    0.50
     vadati
    0.49
     मम
    0.48
     NIT
    0.48
     Respondents
    0.48
    Activations Density 0.000%

    No Known Activations