© 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. 18974
    Prev
    Next
    INDEX
    Explanations

    entrance point, entry level, very long

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

    What is or requires

    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
    el
    0.62
    isin
    0.62
    the
    0.59
    n
    0.57
    know
    0.56
    v
    0.55
    al
    0.54
    represents
    0.54
    agency
    0.54
    ite
    0.54
    POSITIVE LOGITS
     WrestleMania
    0.47
     사용하여
    0.47
    许可证
    0.45
     TreeSet
    0.45
     Illusion
    0.44
     immunosupp
    0.44
     عايز
    0.43
    节日
    0.43
     immunost
    0.43
    😴
    0.43
    Activations Density 0.000%

    No Known Activations