© 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. 9-GEMMASCOPE-2-RES-262K
    4. 8375
    Prev
    Next
    INDEX
    Explanations

    season, seasonal, seasons

    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
    ت
    3.82
    ین
    2.72
    cargar
    2.66
    𝑜
    2.60
    cient
    2.57
    roidism
    2.50
     zeker
    2.44
    sched
    2.43
    ד
    2.43
    ศัพท์
    2.41
    POSITIVE LOGITS
    वानिव
    3.20
    ৩
    2.46
    ্স
    2.40
    ๅ
    2.31
    رة
    2.27
    DBGPRINT
    2.20
     earm
    2.19
    স
    2.14
     cues
    2.12
    logrus
    2.12
    Activations Density 0.176%

    No Known Activations