© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 5685
    Prev
    Next
    INDEX
    Explanations

    psychological impact and aspects

    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
    ৯
    1.59
     spel
    1.33
    या
    1.32
    ți
    1.30
     heroic
    1.30
    ם
    1.30
     abruptly
    1.21
     vehemently
    1.21
    צה
    1.20
     suitors
    1.20
    POSITIVE LOGITS
    sand
    1.64
    say
    1.63
    𝐢
    1.56
    𝐭
    1.55
    𝐧
    1.55
    ര
    1.51
    szer
    1.50
    sman
    1.48
    sit
    1.48
    ли
    1.46
    Activations Density 0.016%

    No Known Activations