© 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. 224251
    Prev
    Next
    INDEX
    Explanations

    command-line instructions or settings

    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
     selfie
    0.41
    ían
    0.38
     हवे
    0.38
    🥰
    0.38
    ㅝ
    0.38
    說是
    0.37
     necessary
    0.37
    因为它
    0.37
     nogle
    0.37
    நோய்
    0.37
    POSITIVE LOGITS
     Pasand
    0.44
     સફળ
    0.43
     aconsel
    0.40
     Entscheid
    0.40
     cenderung
    0.40
    铤
    0.40
     escog
    0.39
     Seguridad
    0.39
     Deployment
    0.39
     karşılaş
    0.39
    Activations Density 0.001%

    No Known Activations