© 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. 229371
    Prev
    Next
    INDEX
    Explanations

    information following conjunctions or periods

    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
     iremos
    0.47
    ⅝
    0.47
     फीचर्स
    0.46
     கிஷோர்
    0.46
    ୁ
    0.46
    iftoire
    0.44
    ตาม
    0.44
     गेले
    0.44
    鈳
    0.44
     मादा
    0.44
    POSITIVE LOGITS
     absur
    0.47
     e
    0.45
     intens
    0.45
     experiential
    0.45
    ↵↵
    0.45
     perceptual
    0.43
     hedon
    0.43
     Inspe
    0.43
     Pareto
    0.43
     ALJ
    0.43
    Activations Density 0.000%

    No Known Activations