© 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. 126121
    Prev
    Next
    INDEX
    Explanations

    instructions and content

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

    questions about language

    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
     pure
    0.46
    ましたが
    0.44
     Simon
    0.44
     Pure
    0.41
     N
    0.40
     jud
    0.40
     Kerry
    0.39
     Regex
    0.39
     persian
    0.39
     linguistic
    0.38
    POSITIVE LOGITS
    íte
    0.47
     ਵਰ
    0.46
     ভূত
    0.44
     baterías
    0.43
    挨拶
    0.43
    ål
    0.43
     മാസ
    0.43
    你应该
    0.42
     tại
    0.41
    뭡
    0.41
    Activations Density 0.000%

    No Known Activations