© 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. 229002
    Prev
    Next
    INDEX
    Explanations

    time and duration

    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
     ک
    0.53
     empat
    0.52
    TPS
    0.48
     madrugada
    0.48
     macam
    0.48
    ço
    0.47
    ører
    0.46
     evapor
    0.46
    ściej
    0.46
     रुचि
    0.46
    POSITIVE LOGITS
    r
    0.49
    也沒有
    0.47
    のですが
    0.46
    煜
    0.44
    動畫
    0.44
    يم
    0.43
    தே
    0.43
    培育
    0.41
    ဓ
    0.41
     bericht
    0.41
    Activations Density 0.001%

    No Known Activations