© 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. 7190
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

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

    the New Drug

    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
    𒌉
    0.40
    Rounding
    0.39
    郯
    0.39
    🎣
    0.37
    CLUD
    0.37
     ট্র্যাক
    0.37
    नीचर
    0.37
    strument
    0.37
     ఇప్పటి
    0.36
    有所
    0.36
    POSITIVE LOGITS
    ¬
    0.41
     Reese
    0.38
     entre
    0.37
     minutos
    0.36
    ]"
    0.35
     bata
    0.35
     महत्वा
    0.35
    premier
    0.35
    peso
    0.35
     |--
    0.35
    Activations Density 0.028%

    No Known Activations