© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 13352
    Prev
    Next
    INDEX
    Explanations

    letter for / to / requesting

    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_12_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
    us
    0.98
    ş
    0.93
    as
    0.86
    Istituto
    0.86
    en
    0.85
    ed
    0.84
    es
    0.82
    ে
    0.82
    不错
    0.82
    は
    0.82
    POSITIVE LOGITS
    山上
    0.80
    ۾
    0.73
    ﹙
    0.73
     มือ
    0.71
    িয়ার
    0.70
     اﻻ
    0.68
     intensification
    0.68
     |_{
    0.66
    වාස
    0.66
    碚
    0.66
    Activations Density 0.001%

    No Known Activations