© 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. 220325
    Prev
    Next
    INDEX
    Explanations

    one understanding

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

    focused attention

    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
    t
    0.73
    c
    0.63
    kom
    0.58
    L
    0.56
    z
    0.55
    l
    0.54
    k
    0.52
    1
    0.50
    s
    0.50
    re
    0.49
    POSITIVE LOGITS
    羥
    0.57
    讒
    0.54
     sangue
    0.53
     ascension
    0.52
    ေသ
    0.52
    逓
    0.52
    imą
    0.52
    投手
    0.51
    釘
    0.51
    経路
    0.50
    Activations Density 0.000%

    No Known Activations