© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38940
    Prev
    Next
    INDEX
    Explanations

    boolean management header

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     criada
    0.46
    다는
    0.44
     criado
    0.43
     *$
    0.43
     Kindergarten
    0.42
     prossima
    0.42
     Dynamics
    0.41
     DURING
    0.40
     Turbulence
    0.40
     Friendly
    0.39
    POSITIVE LOGITS
    rescue
    0.52
    ុស
    0.48
    -{
    0.47
    anées
    0.46
    étera
    0.46
    Ꮈ
    0.45
    ánchez
    0.44
    િર
    0.44
    -[
    0.44
    Bez
    0.43
    Activations Density 0.000%

    No Known Activations