© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 6575
    Prev
    Next
    INDEX
    Explanations

    durations and small amounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ר
    1.79
    й
    1.52
    ро
    1.46
    ي
    1.46
    י
    1.46
    ри
    1.41
    к
    1.40
     regelmatig
    1.39
     dava
    1.38
    лната
    1.36
    POSITIVE LOGITS
    씩
    1.81
    wirtschaft
    1.59
     Doesn
    1.48
    ↵
    1.40
    েই
    1.35
     Couldn
    1.34
    ings
    1.33
    Doesn
    1.31
    疹
    1.30
    тися
    1.23
    Activations Density 0.269%

    No Known Activations