© 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. 40253
    Prev
    Next
    INDEX
    Explanations

    writing desk

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

    awkward phrasing and word choice

    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
    江
    0.50
    🦾
    0.49
    نا
    0.45
    జే
    0.45
     jah
    0.44
    なあ
    0.44
    🧑
    0.44
    언
    0.42
     mangrove
    0.42
    <0xF0>
    0.42
    POSITIVE LOGITS
     również
    0.45
    uvo
    0.44
     Geschäftsführer
    0.43
    ಲ್ಲೂ
    0.43
    roughs
    0.42
    alke
    0.42
    uch
    0.41
    dasarkan
    0.41
    ங்களும்
    0.41
    deviceId
    0.41
    Activations Density 0.000%

    No Known Activations