© 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. 241252
    Prev
    Next
    INDEX
    Explanations

    travel kit

    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
     que
    0.54
     deve
    0.47
    GOOGLE
    0.47
    ਨੀ
    0.46
    ا
    0.45
    กร
    0.45
    Baltimore
    0.44
     maritime
    0.43
    FRING
    0.43
     career
    0.43
    POSITIVE LOGITS
    рифмети
    0.49
     apologised
    0.46
    сэн
    0.45
    렜
    0.45
     texted
    0.45
    ringer
    0.44
     История
    0.44
     dispensed
    0.44
     Некоторые
    0.44
    cą
    0.43
    Activations Density 0.001%

    No Known Activations