Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8245
    Prev
    Next
    INDEX
    Explanations

    but

    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_24_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
    ties
    1.09
    icate
    1.06
    ty
    1.01
     Although
    0.99
     ولك
    0.99
     ولكن
    0.95
    ありますが
    0.95
    ﺃ
    0.95
    toler
    0.92
    ta
    0.91
    POSITIVE LOGITS
    ни
    1.58
    на
    1.55
    ल
    1.51
    ти
    1.49
    ن
    1.41
    न
    1.35
    ну
    1.32
    но
    1.27
    е
    1.19
    ン
    1.19
    Activations Density 0.028%

    No Known Activations