© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 119308
    Prev
    Next
    INDEX
    Explanations

    Premise 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
    ચ
    0.44
    ou
    0.44
    ikes
    0.43
     Election
    0.42
     legislate
    0.42
    ,
    0.42
    選挙
    0.41
    imen
    0.40
    惊
    0.40
    新区
    0.39
    POSITIVE LOGITS
     SCO
    0.47
    brug
    0.47
    тет
    0.46
     refract
    0.46
     Scop
    0.45
    linalg
    0.44
     Joaqu
    0.44
    鞆
    0.44
    都会
    0.43
    SCO
    0.43
    Activations Density 0.000%

    No Known Activations