© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 234809
    Prev
    Next
    INDEX
    Explanations

    take the unexpected out

    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
    waite
    0.52
    ᾖ
    0.50
    ítás
    0.49
    ែន
    0.48
    ні
    0.47
     With
    0.47
    ùng
    0.45
    ick
    0.45
    ict
    0.44
    ві
    0.44
    POSITIVE LOGITS
    "+"|".
    0.52
    getSaveLocation
    0.50
    各类
    0.49
     annih
    0.48
     PIR
    0.47
     یا
    0.47
     baud
    0.47
     menikmati
    0.46
     gladi
    0.46
     PVP
    0.46
    Activations Density 0.000%

    No Known Activations