© 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
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3540
    Prev
    Next
    INDEX
    Explanations

    geographical locations and animals

    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_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
     graces
    1.04
     tamper
    0.99
    शुदा
    0.99
     commitments
    0.90
     речь
    0.90
     Dress
    0.89
    盪
    0.89
     coil
    0.88
     plc
    0.88
     permission
    0.87
    POSITIVE LOGITS
    新疆
    1.37
    ž
    1.30
    🅘
    1.28
    沙漠
    1.26
    尕
    1.25
    自治区
    1.23
    ರ್ಯ
    1.22
     Alaska
    1.17
    k
    1.17
     Alaskan
    1.16
    Activations Density 0.214%

    No Known Activations