© 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. 225057
    Prev
    Next
    INDEX
    Explanations

    listed below, interview by, away from

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

    publisher-specific code

    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
     লিপ
    0.42
    python
    0.42
    LoopBlend
    0.39
    ক্ষিপ্ত
    0.39
    ۸
    0.38
    gom
    0.38
     কির
    0.38
     Tiro
    0.38
    mien
    0.37
    Throws
    0.37
    POSITIVE LOGITS
    ണിത്
    0.49
     entornos
    0.47
     abatement
    0.46
     feedwater
    0.46
     solcher
    0.46
     notor
    0.45
     గవర్
    0.45
    ੰ
    0.45
     autonomia
    0.45
     hydropon
    0.45
    Activations Density 0.001%

    No Known Activations