© 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. 76688
    Prev
    Next
    INDEX
    Explanations

    percentage, apartment, perks

    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
    藓
    0.46
     最后
    0.46
    焐
    0.44
     아름
    0.43
    יר
    0.42
    ADH
    0.42
     değer
    0.41
    ANN
    0.41
    国务院
    0.40
    ર્ડ
    0.40
    POSITIVE LOGITS
    ك
    0.45
    zona
    0.44
     porcent
    0.43
    ،
    0.43
    statt
    0.42
     flota
    0.42
    apartment
    0.42
     perks
    0.41
    ني
    0.41
     Latino
    0.41
    Activations Density 0.006%

    No Known Activations