© 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. 224138
    Prev
    Next
    INDEX
    Explanations

    know what specialists suppliers

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

    9th-13th centuries

    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
    Detectable
    0.51
    Hostname
    0.50
    Determ
    0.47
    Sorter
    0.46
     астро
    0.46
    determ
    0.45
     已
    0.45
    Hosted
    0.45
    EP
    0.45
    Presence
    0.45
    POSITIVE LOGITS
    ی
    0.50
     file
    0.49
     Fay
    0.45
     annoy
    0.45
     SMEs
    0.45
     AVL
    0.45
     those
    0.45
    pdf
    0.44
    ...).
    0.44
     valleys
    0.44
    Activations Density 0.000%

    No Known Activations