© 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. 9041
    Prev
    Next
    INDEX
    Explanations

    behavioral

    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
    ൽ
    2.53
    тра
    2.09
     बजे
    2.07
    äksi
    2.07
     tind
    2.06
    ierungen
    2.06
     faptul
    2.05
     millones
    2.02
    belt
    1.95
     compon
    1.93
    POSITIVE LOGITS
    বিধি
    2.41
     gameState
    2.29
    ो
    2.29
     Bxe
    2.19
    ್ದ
    2.19
    weisen
    2.17
     따라서
    2.17
    ри
    2.15
    ు
    2.14
    it
    2.12
    Activations Density 0.037%

    No Known Activations