© 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. 244698
    Prev
    Next
    INDEX
    Explanations

    responsibility for evaluating

    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
    Repr
    0.47
    SOURCES
    0.46
    ıll
    0.45
    來自
    0.45
    ા
    0.45
    sourced
    0.45
    subj
    0.45
    sop
    0.45
    Lowercase
    0.45
    료
    0.44
    POSITIVE LOGITS
     distancing
    0.51
     Buddhism
    0.49
     seleccionar
    0.48
     complained
    0.45
     banheiro
    0.45
     solidified
    0.45
     reiniciar
    0.44
    ｹ
    0.44
     brigade
    0.43
     stamina
    0.42
    Activations Density 0.000%

    No Known Activations