© 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. 194071
    Prev
    Next
    INDEX
    Explanations

    common problems, get bored, flattering stranger

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

    LEGO words

    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
    thio
    0.50
     কূট
    0.46
    合格
    0.46
    yman
    0.46
    ҫ
    0.46
    ಗದ
    0.45
    पुट
    0.45
    сант
    0.44
    यद
    0.44
    ковый
    0.44
    POSITIVE LOGITS
     de
    0.50
     reina
    0.45
     h
    0.43
     مرحبا
    0.43
     hilo
    0.43
     según
    0.42
     zakład
    0.42
     locale
    0.42
     encontra
    0.42
     find
    0.42
    Activations Density 0.000%

    No Known Activations