© 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. 123362
    Prev
    Next
    INDEX
    Explanations

    counting from zero

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

    dates, network, simple, non-invasive

    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
    ts
    0.50
    ities
    0.45
    pitch
    0.45
    g
    0.44
    '
    0.44
     configuration
    0.43
    human
    0.43
    barrier
    0.43
    closes
    0.43
    ',
    0.43
    POSITIVE LOGITS
    珽
    0.51
     Faktoren
    0.48
    öö
    0.47
     transfert
    0.46
    ৃতা
    0.46
     Resting
    0.46
    砳
    0.46
    উট
    0.45
    인은
    0.45
     elastin
    0.45
    Activations Density 0.001%

    No Known Activations