© 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. 244955
    Prev
    Next
    INDEX
    Explanations

    monthly schedule

    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
    よそ
    0.46
    🟠
    0.43
    hearted
    0.42
     refere
    0.42
    綿
    0.40
     phenomena
    0.40
     stature
    0.40
    ❱
    0.40
    หว่าง
    0.40
     betreff
    0.40
    POSITIVE LOGITS
    Է
    0.53
     économiques
    0.52
     hacemos
    0.49
    Allora
    0.49
     تقسيم
    0.46
    ک
    0.46
    illas
    0.46
    Cómo
    0.46
     کوي
    0.46
     echoed
    0.46
    Activations Density 0.000%

    No Known Activations