© 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. 184067
    Prev
    Next
    INDEX
    Explanations

    information search or topic specification

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

    artist's sketch

    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
    emens
    0.53
    ણો
    0.52
    eties
    0.47
    rainment
    0.47
    enaries
    0.46
     तूती
    0.46
    "/"
    0.46
    ancies
    0.46
    rocities
    0.45
    :~
    0.45
    POSITIVE LOGITS
     కో
    0.52
     ktore
    0.51
     be
    0.50
     هذا
    0.49
    兌
    0.49
     würde
    0.48
     تاريخ
    0.47
     avrebbe
    0.47
    ية
    0.46
     hätte
    0.46
    Activations Density 0.001%

    No Known Activations