© 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. 232771
    Prev
    Next
    INDEX
    Explanations

    online article

    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
     состоя
    0.49
     Hatton
    0.47
    mathscr
    0.45
     Henrique
    0.44
    ]").
    0.43
     যেন
    0.43
    ";
    0.42
    imgPath
    0.42
     backseat
    0.42
    ১২
    0.42
    POSITIVE LOGITS
    ون
    0.55
    ე
    0.54
    𝐭
    0.50
     allotment
    0.49
    ή
    0.49
    elor
    0.48
    कौन
    0.48
    er
    0.48
    ות
    0.48
    ເຄ
    0.48
    Activations Density 0.000%

    No Known Activations