© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 139245
    Prev
    Next
    INDEX
    Explanations

    universe or abstract location

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    e
    0.71
    et
    0.66
    o
    0.65
    en
    0.65
    .
    0.64
    ent
    0.61
    ti
    0.61
    >
    0.61
     a
    0.59
    ot
    0.59
    POSITIVE LOGITS
     scrittura
    0.67
     ragazzo
    0.63
     gioco
    0.62
     paralelas
    0.61
     recorrido
    0.59
     pouce
    0.58
     módulo
    0.58
     ла
    0.57
     دنیا
    0.57
     funzione
    0.57
    Activations Density 0.000%

    No Known Activations