© 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. 41730
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    verbatim environment

    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
    io
    0.50
            
    0.49
    の水
    0.48
     水
    0.47
    id
    0.46
     &_
    0.46
    in
    0.46
        
    0.44
    u
    0.43
    ui
    0.43
    POSITIVE LOGITS
     οποία
    0.46
     laquelle
    0.45
     inexplicable
    0.42
     hvilket
    0.42
    蝙
    0.42
    ائن
    0.40
     котором
    0.40
     Tottenham
    0.40
     Statutes
    0.40
     három
    0.40
    Activations Density 0.000%

    No Known Activations