© 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. 208920
    Prev
    Next
    INDEX
    Explanations

    receiving updates and notifications

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

    language understanding

    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
     Overflow
    0.54
     Coatings
    0.49
    U
    0.47
     Monitoring
    0.46
    T
    0.46
     Dighe
    0.46
    ubov
    0.46
    Recogn
    0.45
     Recognition
    0.45
     Recognizing
    0.45
    POSITIVE LOGITS
     blots
    0.43
     pledge
    0.42
     resposta
    0.41
     kurie
    0.41
    IVOS
    0.40
     *$
    0.40
    気分
    0.40
    ***************/
    0.40
    "/></
    0.40
     rupee
    0.40
    Activations Density 0.000%

    No Known Activations