© 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. 182540
    Prev
    Next
    INDEX
    Explanations

    credit risk

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

    professional license, roleplay, laptop, system, recipe, request

    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
    d
    0.51
    y
    0.49
    c
    0.49
    b
    0.46
    Ev
    0.46
    ilar
    0.45
    ě
    0.45
    El
    0.44
    Cleaning
    0.44
    cleaned
    0.43
    POSITIVE LOGITS
     incarceration
    0.54
    ти
    0.53
     reforestation
    0.52
    धपुर
    0.51
     автобу
    0.51
     изобре
    0.51
     तस्वी
    0.49
     eyeglasses
    0.49
     द्वीप
    0.49
    त्स
    0.49
    Activations Density 0.000%

    No Known Activations