© 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. 152501
    Prev
    Next
    INDEX
    Explanations

    specialists work

    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
    ન્મ
    0.49
    دی
    0.49
    ズ
    0.48
    Q
    0.48
    Z
    0.46
    H
    0.46
    ˧
    0.45
    藝
    0.44
    نم
    0.44
    W
    0.44
    POSITIVE LOGITS
    olata
    0.52
     hvis
    0.51
    ésie
    0.47
     באמצע
    0.47
     occult
    0.47
    ůže
    0.47
     mort
    0.46
     לאחר
    0.44
    หลังจาก
    0.44
     집에
    0.44
    Activations Density 0.000%

    No Known Activations