© 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. 129024
    Prev
    Next
    INDEX
    Explanations

    providing these links

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

    specification, designed, accuracy

    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
    म
    0.68
    م
    0.56
    カ
    0.53
    ма
    0.53
    ন
    0.52
    ن
    0.52
    न
    0.51
    കാ
    0.51
    中年
    0.51
    过多
    0.51
    POSITIVE LOGITS
     disabled
    0.49
    )
    0.48
     led
    0.48
     rash
    0.47
     b
    0.47
     AND
    0.47
     list
    0.47
     flipped
    0.47
    gga
    0.47
     NEED
    0.46
    Activations Density 0.000%

    No Known Activations