© 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. 46584
    Prev
    Next
    INDEX
    Explanations

    operation Danger

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

    concentric circles, overlapping shapes

    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
    咥
    0.46
    ન
    0.42
    レル
    0.42
    Wallet
    0.41
    承认
    0.40
    Portal
    0.40
    ジット
    0.40
    佉
    0.39
    打造
    0.39
    Starred
    0.39
    POSITIVE LOGITS
     gradual
    0.49
     someday
    0.47
     irreg
    0.47
     monitored
    0.46
     forskjellige
    0.46
     cayenne
    0.44
     overlap
    0.43
     interrelated
    0.43
     powinien
    0.43
     remedial
    0.41
    Activations Density 0.001%

    No Known Activations