© 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. 217101
    Prev
    Next
    INDEX
    Explanations

    individually turning entertainment run reputation grocery

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

    necessarily mean

    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
    Ver
    0.53
    Lemon
    0.53
    gegevens
    0.52
    Jim
    0.49
    Y
    0.48
    Leg
    0.48
    Timeline
    0.47
    Recent
    0.47
    Nik
    0.47
    P
    0.47
    POSITIVE LOGITS
     ada
    0.46
    द्दा
    0.45
     sai
    0.45
     kira
    0.44
     calcS
    0.42
     stemmed
    0.42
    说话
    0.42
     ठिकाणी
    0.42
     bap
    0.42
    ष्णा
    0.42
    Activations Density 0.001%

    No Known Activations