© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6626
    Prev
    Next
    INDEX
    Explanations

    instant gratification, overdue things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    millimeters
    0.47
     Drainage
    0.46
    Flu
    0.46
    uero
    0.43
    +
    0.43
    helf
    0.43
     Spill
    0.42
     Bench
    0.42
     بیر
    0.42
    ర్చ
    0.42
    POSITIVE LOGITS
     uneasy
    0.46
    lbrakk
    0.46
     incertid
    0.44
     españa
    0.43
     obec
    0.41
    സിന്റെ
    0.41
     gotovo
    0.40
    ﻪ
    0.40
    ્રો
    0.40
     ekstrem
    0.40
    Activations Density 0.018%

    No Known Activations