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. 17-GEMMASCOPE-2-RES-65K
    4. 47301
    Prev
    Next
    INDEX
    Explanations

    col- followed by number

    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_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
    ﺀ
    1.59
    னர்
    1.49
    眼神
    1.48
    altering
    1.46
    újo
    1.44
     foray
    1.43
    oloj
    1.42
    ankle
    1.42
    स्करण
    1.41
    ة
    1.41
    POSITIVE LOGITS
    ش
    1.59
    いきます
    1.42
    ত
    1.31
    isations
    1.22
    Equivalent
    1.20
    ta
    1.18
    ට
    1.17
    ো
    1.16
    ين
    1.15
    र
    1.14
    Activations Density 0.002%

    No Known Activations