© 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. 195090
    Prev
    Next
    INDEX
    Explanations

    whenever investors

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

    Old Man Pine

    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
     WebView
    0.52
    }^{+}
    0.48
     explored
    0.47
    }^{+}\
    0.46
    పథ
    0.46
     strtok
    0.45
     championed
    0.45
    ಈ
    0.45
     Diff
    0.45
     целях
    0.45
    POSITIVE LOGITS
    akin
    0.50
     slay
    0.50
    kli
    0.46
    tob
    0.45
    hasa
    0.44
    magnet
    0.44
    USA
    0.44
    killer
    0.44
    lö
    0.43
    bapt
    0.43
    Activations Density 0.001%

    No Known Activations