© 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. 211559
    Prev
    Next
    INDEX
    Explanations

    actions of others

    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
    ตัวเอง
    0.48
     собой
    0.47
     സ്ഥല
    0.45
    +"
    0.44
     alles
    0.43
     ದಾ
    0.42
    வரை
    0.41
    स्थल
    0.41
    izada
    0.41
     *}
    0.41
    POSITIVE LOGITS
     others
    0.59
     bureaucrats
    0.54
     marketers
    0.53
     chemists
    0.53
     Others
    0.52
     pundits
    0.51
     lobbyists
    0.51
     politicians
    0.50
     statesmen
    0.48
     scholars
    0.48
    Activations Density 0.016%

    No Known Activations