© 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-65K
    7. 52735
    Prev
    Next
    INDEX
    Explanations

    Intent:

    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_65k_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
    మవు
    0.46
    و
    0.46
     Might
    0.46
     Termination
    0.46
     Reven
    0.45
     Peace
    0.43
    i
    0.43
     Bé
    0.43
     Maximilian
    0.42
    alignat
    0.42
    POSITIVE LOGITS
    Shortcut
    0.49
     aerial
    0.48
    罠
    0.46
    ugia
    0.45
    Fizz
    0.45
    Dive
    0.44
     پی
    0.43
    COMM
    0.43
    Comput
    0.43
    Tha
    0.43
    Activations Density 0.004%

    No Known Activations