© 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-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 30837
    Prev
    Next
    INDEX
    Explanations

    game-changer

    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
    ↵
    1.27
     expon
    1.24
    t
    1.20
     depred
    1.18
     annum
    1.16
    นี้
    1.14
     acred
    1.13
     frequented
    1.13
    करण
    1.12
     burgeoning
    1.12
    POSITIVE LOGITS
    ו
    1.75
    ९
    1.56
    יר
    1.36
    es
    1.35
    י
    1.35
    فه
    1.25
    ي
    1.23
    و
    1.23
    o
    1.21
    nings
    1.20
    Activations Density 0.001%

    No Known Activations