© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 14868
    Prev
    Next
    INDEX
    Explanations

    de

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
    ళ్ళు
    0.95
     vrlo
    0.90
    /
    0.87
     그것
    0.84
     ह्या
    0.83
     :
    0.82
    :
    0.82
     /
    0.81
     Muito
    0.80
    ία
    0.80
    POSITIVE LOGITS
     депутат
    1.14
     ಸಿನಿ
    1.10
     quarterfinals
    1.10
     slammed
    1.06
     sostuvo
    1.04
     whopping
    1.03
     hubo
    1.02
     semifinals
    1.01
    hattisgarh
    1.01
     भाजपा
    1.00
    Activations Density 0.050%

    No Known Activations