© 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. 3688
    Prev
    Next
    INDEX
    Explanations

    LGBTQ youth support

    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
    يف
    1.28
    オシャレ
    1.26
     باتوں
    1.24
    ري
    1.22
     attenu
    1.18
    乀
    1.16
    惫
    1.16
     rmse
    1.13
    古墳
    1.13
    يفي
    1.13
    POSITIVE LOGITS
    ed
    1.68
    Time
    1.45
    ening
    1.39
    et
    1.35
    ly
    1.27
    ischen
    1.27
    led
    1.26
    PROTE
    1.26
    Trail
    1.24
    ì
    1.24
    Activations Density 0.042%

    No Known Activations