© 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. 184442
    Prev
    Next
    INDEX
    Explanations

    Wrote: followed by colon

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

    | ritualistic exclusivity

    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
    ].
    0.50
    ten
    0.48
    ”
    0.47
    antown
    0.46
    encode
    0.46
    ]
    0.46
    izio
    0.45
    nat
    0.45
    ceans
    0.44
     ].
    0.44
    POSITIVE LOGITS
     오늘도
    0.56
     सड़कों
    0.47
     celulares
    0.45
     पैदा
    0.45
     күн
    0.45
    점
    0.44
     ожи
    0.44
    부가
    0.43
    오늘
    0.43
    心が
    0.43
    Activations Density 0.000%

    No Known Activations