© 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. 174909
    Prev
    Next
    INDEX
    Explanations

    service delivery

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

    created by Google DeepMind

    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
     determinación
    0.54
    ॰ऍ
    0.53
    アナ
    0.53
     tubercles
    0.52
     представления
    0.52
     uzys
    0.52
    관
    0.52
    зывать
    0.51
     détermination
    0.51
    <unused55>
    0.50
    POSITIVE LOGITS
    o
    0.63
    social
    0.58
    al
    0.57
    x
    0.54
    ol
    0.54
    dipl
    0.53
    t
    0.53
    xt
    0.52
    m
    0.52
    labor
    0.51
    Activations Density 0.001%

    No Known Activations