© 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. 201795
    Prev
    Next
    INDEX
    Explanations

    to make

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

    Xinjiang, Square, Size, Validator, weld

    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
     numeric
    0.52
     agricultura
    0.47
     a
    0.45
     minister
    0.45
     relativa
    0.45
     ministers
    0.45
     subj
    0.45
     parcialmente
    0.45
     border
    0.44
     liv
    0.44
    POSITIVE LOGITS
    remember
    0.56
    ت
    0.50
    avos
    0.49
     Plugging
    0.48
    }_{+}
    0.48
    HK
    0.47
    essence
    0.46
     Remember
    0.46
    မယ်
    0.45
     Điều
    0.45
    Activations Density 0.000%

    No Known Activations