© 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. 44088
    Prev
    Next
    INDEX
    Explanations

    saying something

    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
    د
    1.32
    스
    1.30
    ス
    1.26
    д
    1.25
    在
    1.25
    년대
    1.20
    이
    1.19
    تا
    1.18
    ه
    1.17
    어
    1.16
    POSITIVE LOGITS
    7
    1.22
    ፈላጊ
    1.16
     cursory
    1.07
     prokary
    1.06
    1
    1.06
     wyłącznie
    1.05
    5
    1.02
    9
    1.01
    PERCENT
    0.99
     prophylaxis
    0.98
    Activations Density 0.003%

    No Known Activations