© 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. 61710
    Prev
    Next
    INDEX
    Explanations

    action and impact

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

    matrix decomposition

    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
    ្ល
    0.52
    appartement
    0.50
    azadas
    0.49
    ָ
    0.46
    ون
    0.46
    样例
    0.45
    א
    0.45
    Ա
    0.45
     заро
    0.44
    DataMat
    0.44
    POSITIVE LOGITS
     POL
    0.53
     blasting
    0.53
     blockbuster
    0.52
     limousine
    0.52
     bomb
    0.50
     PUT
    0.50
     binge
    0.50
     policeman
    0.49
     bestseller
    0.48
     LIT
    0.48
    Activations Density 0.000%

    No Known Activations