© 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. 208754
    Prev
    Next
    INDEX
    Explanations

    brushes, victim, certain

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

    code string processing

    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
    珽
    0.49
     Moraes
    0.48
    琇
    0.47
    FFEE
    0.47
    성은
    0.46
    廷
    0.46
    кала
    0.46
    angering
    0.44
    热水
    0.44
     Oliveira
    0.44
    POSITIVE LOGITS
     pred
    0.48
    𝐝
    0.46
     triage
    0.45
    ichi
    0.44
     subset
    0.43
     плат
    0.43
    ૩
    0.43
    ูด
    0.43
     leiden
    0.43
     privadas
    0.43
    Activations Density 0.000%

    No Known Activations