© 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. 30449
    Prev
    Next
    INDEX
    Explanations

    place, permitted, issues, testing, supported, flee, respect, applications, teach

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

    break down into

    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
     nějak
    0.46
     vår
    0.46
    }}$.
    0.45
     ().
    0.44
    الوجی
    0.44
     ].
    0.44
     }.
    0.43
     ).
    0.43
     выгля
    0.43
     вашей
    0.43
    POSITIVE LOGITS
     also
    0.82
    also
    0.82
     также
    0.74
     настолько
    0.70
     ONLY
    0.67
    Also
    0.66
     mainly
    0.64
     також
    0.64
     primarily
    0.63
    mainly
    0.63
    Activations Density 0.160%

    No Known Activations