© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 6406
    Prev
    Next
    INDEX
    Explanations

    pictures, photos, or images

    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_16_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
    C
    0.59
    ه
    0.52
    V
    0.50
    0
    0.49
    ',
    0.48
    no
    0.46
    k
    0.44
    on
    0.43
    ンテ
    0.43
    int
    0.42
    POSITIVE LOGITS
     vì
    0.43
     blossoming
    0.42
     дорого
    0.42
     brick
    0.39
     bombardment
    0.39
    یرے
    0.38
     YouTube
    0.38
     girlfriend
    0.37
     makeup
    0.36
     πλή
    0.36
    Activations Density 0.000%

    No Known Activations