© 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. 31442
    Prev
    Next
    INDEX
    Explanations

    readonly keyword usage

    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
     серпня
    1.26
     =",
    1.26
     *)
    1.24
     PlayerSelector
    1.24
     admirably
    1.19
    したのは
    1.18
    पिक्सल
    1.18
    tedir
    1.16
    ⸜
    1.16
     stycznia
    1.15
    POSITIVE LOGITS
    ката
    1.33
    ن
    1.27
    ت
    1.26
    ारी
    1.20
    т
    1.18
    ون
    1.16
    AUT
    1.14
    نف
    1.14
    ло
    1.13
    rée
    1.11
    Activations Density 0.000%

    No Known Activations