© 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. 169174
    Prev
    Next
    INDEX
    Explanations

    prior consent

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

    text inside curly brackets

    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
    usin
    0.51
    แค
    0.51
    igere
    0.48
    떳
    0.47
     enfoc
    0.47
    nero
    0.47
    ('.')
    0.46
    orsanız
    0.46
    㬶
    0.46
    usakan
    0.45
    POSITIVE LOGITS
     niezwy
    0.49
     Wear
    0.48
     can
    0.47
     Components
    0.47
     Speakers
    0.47
     COMPONENTS
    0.47
     লিখিত
    0.46
     Languages
    0.46
     Recent
    0.46
     Membranes
    0.46
    Activations Density 0.000%

    No Known Activations