© 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. 101131
    Prev
    Next
    INDEX
    Explanations

    layered complex concepts

    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
    żliw
    0.53
    ようで
    0.49
    žno
    0.46
     accountants
    0.45
    w
    0.44
    ăm
    0.44
    ngày
    0.43
     pēc
    0.43
     त्यांच्या
    0.42
    ॕ
    0.42
    POSITIVE LOGITS
     bleeding
    0.41
     acidic
    0.39
    🌶
    0.38
     inoltre
    0.37
     Troubleshooting
    0.37
    เลือด
    0.37
    癢
    0.37
     sour
    0.36
    Toxic
    0.36
     Respiratory
    0.36
    Activations Density 0.017%

    No Known Activations