© 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. 9-GEMMASCOPE-2-RES-16K
    7. 0
    Prev
    Next
    INDEX
    Explanations

    closing punctuation or non-alphanumeric characters

    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_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
    на
    0.73
    csc
    0.71
    ು
    0.69
    就是一个
    0.66
    тков
    0.65
    casa
    0.65
    నకు
    0.64
    c
    0.63
    cando
    0.63
    gtr
    0.62
    POSITIVE LOGITS
    ট
    0.61
    ro
    0.61
    ities
    0.60
    জন
    0.59
    ри
    0.58
    os
    0.57
    klore
    0.57
    וי
    0.56
    M
    0.55
    ot
    0.55
    Activations Density 0.676%

    No Known Activations