© 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. 40-GEMMASCOPE-2-RES-262K
    7. 211632
    Prev
    Next
    INDEX
    Explanations

    lists or bullet points

    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_40_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
     SO
    0.43
     salaire
    0.40
     Dirty
    0.39
    ponen
    0.39
     Trail
    0.38
    quito
    0.38
    𝘐
    0.38
     Express
    0.38
     scrambled
    0.37
    sej
    0.37
    POSITIVE LOGITS
     неправи
    0.41
    점이
    0.39
    verein
    0.38
    ü
    0.38
    aszt
    0.38
     pétales
    0.38
    ounters
    0.37
     illusion
    0.37
    illusion
    0.37
     इस्लाम
    0.37
    Activations Density 0.000%

    No Known Activations