© 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. 123152
    Prev
    Next
    INDEX
    Explanations

    Soccer Player, product manufacturers, CGT event, experimental, Lord

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

    problem statement

    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
    c
    0.60
    lo
    0.54
    D
    0.51
    ts
    0.51
    s
    0.50
    g
    0.50
    w
    0.50
    l
    0.49
    том
    0.49
    m
    0.48
    POSITIVE LOGITS
    晾
    0.48
     অনুস
    0.47
     modell
    0.47
    缴
    0.46
     poj
    0.44
     gruppi
    0.43
     ою
    0.43
     इंट्रो
    0.41
     göra
    0.41
     modeller
    0.41
    Activations Density 0.000%

    No Known Activations