© 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. 138022
    Prev
    Next
    INDEX
    Explanations

    iron vanity

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

    sets the stage

    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
    ცი
    0.55
    ﾆ
    0.52
    ｺ
    0.50
    یا
    0.50
     puedas
    0.50
    투
    0.47
     بنابراین
    0.46
    ｵ
    0.46
    リスト
    0.46
    ignement
    0.46
    POSITIVE LOGITS
     hurd
    0.57
     august
    0.47
    leece
    0.44
     Set
    0.44
    ্্র
    0.43
     ဝ
    0.42
     toko
    0.42
     story
    0.42
    égal
    0.41
     rug
    0.41
    Activations Density 0.000%

    No Known Activations