© 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. 200149
    Prev
    Next
    INDEX
    Explanations

    learning more, missing home or person

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

    often, slightly, multiple, several

    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
     швидко
    0.57
    𝘼
    0.52
     раствора
    0.52
     कैन
    0.51
    Khokhlov
    0.51
     пло
    0.50
     تباہ
    0.49
     різних
    0.49
    🫣
    0.49
     lancer
    0.49
    POSITIVE LOGITS
    it
    0.44
    attached
    0.42
    details
    0.41
     US
    0.40
    oxi
    0.40
    as
    0.40
    asis
    0.39
     certeza
    0.39
    ISI
    0.39
    }</
    0.39
    Activations Density 0.001%

    No Known Activations