© 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. 1099
    Prev
    Next
    INDEX
    Explanations

    emphasis or quoting

    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
    a
    1.55
    es
    1.46
    ת
    1.40
    м
    1.31
    л
    1.28
    as
    1.24
    en
    1.23
    ي
    1.18
    u
    1.17
    ি
    1.16
    POSITIVE LOGITS
    য়ের
    1.36
    <unused2121>
    1.25
    <unused2130>
    1.19
    য়ের
    1.19
    siswa
    1.08
    <unused197>
    1.06
    s
    1.05
    <unused2186>
    1.04
    gaben
    1.04
    <unused1887>
    1.03
    Activations Density 0.718%

    No Known Activations