© 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. 160263
    Prev
    Next
    INDEX
    Explanations

    absent in, others like, 0 of

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

    input event processing

    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
     arreglo
    0.50
    פ
    0.48
     supremac
    0.46
     indicaciones
    0.46
     caballos
    0.45
     pare
    0.45
     hace
    0.45
     сет
    0.44
     conditioners
    0.44
     deposito
    0.44
    POSITIVE LOGITS
    ร้าง
    0.47
    峣
    0.45
     Clay
    0.45
     Proficiency
    0.44
    ራስ
    0.43
     Milling
    0.42
    铤
    0.42
     Brug
    0.42
     Maloney
    0.42
     Warrington
    0.41
    Activations Density 0.000%

    No Known Activations