© 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. 191664
    Prev
    Next
    INDEX
    Explanations

    high cheekbones

    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
     .+
    0.42
    डनी
    0.39
    嫚
    0.39
    (+
    0.38
     drainage
    0.38
     бренда
    0.38
    бурга
    0.38
     అనుమ
    0.38
     миро
    0.37
     Drainage
    0.37
    POSITIVE LOGITS
    jelasan
    0.42
     проходи
    0.38
    arus
    0.37
    孰
    0.36
    hasil
    0.36
    耂
    0.36
     McQu
    0.35
    JQ
    0.35
    rzost
    0.34
    cellaneous
    0.34
    Activations Density 0.000%

    No Known Activations