© 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. 39372
    Prev
    Next
    INDEX
    Explanations

    quotes, business, writing, L

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

    concepts tied to descriptions

    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
    r
    0.57
    H
    0.47
     onda
    0.47
     was
    0.47
    I
    0.46
    wave
    0.45
    S
    0.45
    O
    0.45
    W
    0.44
    Y
    0.44
    POSITIVE LOGITS
    ēi
    0.60
     způ
    0.55
     үш
    0.55
     多く
    0.55
    蜷
    0.52
     可愛
    0.50
     ถูก
    0.49
    ปก
    0.48
     말
    0.48
     জনসাধারণ
    0.48
    Activations Density 0.000%

    No Known Activations