© 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. 227683
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

    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
     favorit
    0.54
     kontrakt
    0.54
     compartilh
    0.53
     geeign
    0.51
    ún
    0.51
     ní
    0.51
     distaste
    0.50
    𝐭
    0.50
     underwriting
    0.50
    𝟎
    0.50
    POSITIVE LOGITS
    Res
    0.51
     சென்னைய
    0.48
     *(
    0.48
    ayas
    0.45
     Visits
    0.45
    D
    0.45
     Viruses
    0.44
     (
    0.44
     resulted
    0.44
    Days
    0.44
    Activations Density 0.001%

    No Known Activations