© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1977
    Prev
    Next
    INDEX
    Explanations

    recursive, criminals, protocol, encryption, artists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_16k_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
     hydrazine
    0.84
    మ్
    0.81
    ﻡ
    0.79
    tains
    0.75
     bijzonder
    0.73
     versatile
    0.73
    ﺭ
    0.73
    돛
    0.73
     netherlands
    0.73
    нняя
    0.72
    POSITIVE LOGITS
    ari
    0.74
    ara
    0.74
    esh
    0.71
    ри
    0.69
    [
    0.68
     arrested
    0.68
    *
    0.66
     forge
    0.65
    **
    0.64
    erez
    0.63
    Activations Density 0.010%

    No Known Activations