© 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
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 10440
    Prev
    Next
    INDEX
    Explanations

    the short answer is

    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
    ות
    2.36
    ্ড
    2.34
    er
    2.34
    দ
    2.30
    den
    2.29
    ীর
    2.27
    in
    2.25
     Pik
    2.25
    dari
    2.14
    ীদের
    2.13
    POSITIVE LOGITS
     stature
    2.56
    ال
    2.55
    bread
    2.47
     lived
    2.20
    ऎ
    2.19
     hostilities
    2.13
    falls
    2.12
     ascertain
    2.11
    Provenance
    2.10
    marginBottom
    2.07
    Activations Density 0.319%

    No Known Activations