© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 56355
    Prev
    Next
    INDEX
    Explanations

    but it

    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_65k_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
    也
    0.45
    Ec
    0.43
     Ec
    0.42
     també
    0.41
     also
    0.40
     complex
    0.40
     também
    0.40
     también
    0.40
    DF
    0.39
    "];
    0.39
    POSITIVE LOGITS
     didn
    0.45
    嚷
    0.44
     seemed
    0.44
    นะนำ
    0.43
     parecía
    0.43
     trouvait
    0.41
    tted
    0.41
     refused
    0.40
     eivät
    0.40
     बैड
    0.40
    Activations Density 0.056%

    No Known Activations