© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 146098
    Prev
    Next
    INDEX
    Explanations

    trailing around, reception area

    np_acts-logits-general · gemini-2.5-flash-lite

    take... be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lebanon
    0.50
    ]_
    0.44
    ''_
    0.43
     Validation
    0.42
    헉
    0.42
    рто
    0.42
    পৃ
    0.41
    _
    0.41
     당신
    0.41
     لبنان
    0.41
    POSITIVE LOGITS
    kimi
    0.52
    ämään
    0.49
    ar
    0.48
     ज्वाला
    0.48
    ǎi
    0.47
    કી
    0.47
    uksia
    0.46
     acestea
    0.46
    ää
    0.46
    passt
    0.46
    Activations Density 0.000%

    No Known Activations