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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 28602
    Prev
    Next
    INDEX
    Explanations

    lack of characteristics or facial hair

    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_40_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
    "?>
    0.44
     maxY
    0.41
     smoothing
    0.40
    😜
    0.40
     tots
    0.39
     protective
    0.39
     Drafting
    0.39
     Inclusive
    0.39
    isterschaften
    0.38
     Oblast
    0.38
    POSITIVE LOGITS
     arranque
    0.40
    Performance
    0.38
    intent
    0.38
    heavy
    0.38
    nbsp
    0.37
    高い
    0.37
    重
    0.37
    hto
    0.37
    Eb
    0.34
    performance
    0.34
    Activations Density 0.000%

    No Known Activations