© 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. 161823
    Prev
    Next
    INDEX
    Explanations

    court documents, online quotes, crossword clue

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

    discussing roles and characteristics

    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
     costas
    0.49
    ів
    0.48
     присут
    0.48
     tér
    0.46
    }_{
    0.45
     apare
    0.44
     depan
    0.44
    ű
    0.44
     vati
    0.44
    ujú
    0.43
    POSITIVE LOGITS
    scheduler
    0.49
    nominated
    0.47
    royalblue
    0.47
    冬天
    0.46
    bouncer
    0.45
    emergency
    0.45
    syllabus
    0.45
    WC
    0.45
    WEATHER
    0.44
    ten
    0.44
    Activations Density 0.001%

    No Known Activations