© 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. 237948
    Prev
    Next
    INDEX
    Explanations

    version electedlaw theRead fourepisode the

    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
     loa
    0.52
     trusting
    0.48
     ट्रस्ट
    0.47
    钱
    0.47
    錢
    0.45
    ram
    0.44
     hoa
    0.44
    欝
    0.44
     લો
    0.43
     board
    0.43
    POSITIVE LOGITS
     endIndex
    0.53
    DepartTime
    0.52
    }/>
    0.46
     aplikace
    0.46
    Bz
    0.45
    стви
    0.45
    Dieser
    0.45
    a
    0.45
     besonderen
    0.44
     Spitzen
    0.44
    Activations Density 0.000%

    No Known Activations