© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 8776
    Prev
    Next
    INDEX
    Explanations

    shock value

    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
    s
    2.28
    ের
    2.05
    ים
    1.86
    u
    1.80
    annya
    1.74
     presence
    1.68
     stairs
    1.64
    কানিক্যাল
    1.63
    ুল
    1.59
     hills
    1.59
    POSITIVE LOGITS
    يع
    1.80
    warts
    1.72
    דת
    1.59
    ੀ
    1.59
    orro
    1.59
     scritto
    1.58
    有可能
    1.56
    样
    1.56
    NEG
    1.55
    PS
    1.55
    Activations Density 0.008%

    No Known Activations