© 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. 59383
    Prev
    Next
    INDEX
    Explanations

    indicator, scald, Apple, door, Scholarship

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

    contrarian approaches

    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
    දි
    0.52
    ′
    0.49
    to
    0.44
    国立
    0.41
     भोले
    0.40
    Statistical
    0.40
     Nebraska
    0.40
     Slade
    0.39
     स्टैट
    0.39
    \
    0.39
    POSITIVE LOGITS
    ᄏ
    0.51
     diligently
    0.46
    DataMat
    0.45
     philosophies
    0.45
     Regularly
    0.44
     progenitors
    0.44
    కీయ
    0.44
     onus
    0.44
    載
    0.43
     equivoc
    0.43
    Activations Density 0.000%

    No Known Activations