© 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. 111654
    Prev
    Next
    INDEX
    Explanations

    you or self reference

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

    understanding complex relationships

    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
    daughters
    0.46
    9
    0.44
    েল
    0.43
    டுகள்
    0.43
    म
    0.43
    ון
    0.42
    8
    0.42
    引领
    0.42
     ட
    0.41
    Elephant
    0.41
    POSITIVE LOGITS
    BitCount
    0.47
     ব্যক্তির
    0.47
     allow
    0.45
     شخصیت
    0.44
     Beziehung
    0.44
     현재
    0.44
     식으로
    0.43
     relationship
    0.43
     ഉള്ള
    0.42
     relazione
    0.42
    Activations Density 0.000%

    No Known Activations