Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7369
    Prev
    Next
    INDEX
    Explanations

    private network

    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_9_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
    ก
    1.75
    ০
    1.65
    к
    1.57
    กก
    1.38
    何を
    1.35
    ulkan
    1.35
    öz
    1.33
     bilangan
    1.32
    т
    1.31
    ISTRATION
    1.30
    POSITIVE LOGITS
    causing
    1.43
    বা
    1.30
    𝓙
    1.30
    fatal
    1.30
     واحده
    1.27
    િસ્
    1.23
    Delete
    1.21
     cancers
    1.20
    Determine
    1.18
    libexec
    1.18
    Activations Density 0.000%

    No Known Activations