© 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. 191239
    Prev
    Next
    INDEX
    Explanations

    lung diseases and precursors

    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
    쥬
    0.44
    }}-\
    0.40
    ('-');
    0.38
     Lunar
    0.38
    isiones
    0.37
    يو
    0.37
     collinear
    0.37
    あげ
    0.37
    zoic
    0.36
     pranzo
    0.36
    POSITIVE LOGITS
    Kumar
    0.43
    hede
    0.40
    vall
    0.40
    磵
    0.38
     BCS
    0.38
     Rafi
    0.38
    eby
    0.38
     փ
    0.38
    bon
    0.38
     pamphlets
    0.38
    Activations Density 0.000%

    No Known Activations