© 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. 224951
    Prev
    Next
    INDEX
    Explanations

    for he

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

    lists of items

    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
    pg
    0.53
    нары
    0.53
    0
    0.53
    V
    0.52
    6
    0.51
    ij
    0.51
    1
    0.50
    9
    0.50
     Travel
    0.48
    ды
    0.48
    POSITIVE LOGITS
     விளை
    0.55
    ദേശ
    0.54
     학
    0.53
    ContactBundle
    0.52
     괴
    0.51
     transformada
    0.50
     ക
    0.50
     அதிகரிக்கிறது
    0.50
     ത
    0.49
     소비자
    0.49
    Activations Density 0.000%

    No Known Activations