© 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. 28480
    Prev
    Next
    INDEX
    Explanations

    code syntax delimiters

    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
    tr
    0.49
     k
    0.48
     собственных
    0.44
     Laut
    0.42
    nih
    0.42
     exécut
    0.41
     Front
    0.41
     Tanner
    0.41
     Ei
    0.40
     K
    0.40
    POSITIVE LOGITS
    Comma
    0.40
    шенный
    0.39
    Humidity
    0.38
    electrolyte
    0.37
    恜
    0.37
    ላይ
    0.37
    ன்மை
    0.37
     enviable
    0.37
    ளர்
    0.36
    раз
    0.36
    Activations Density 0.001%

    No Known Activations