© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 8250
    Prev
    Next
    INDEX
    Explanations

    bone

    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
    ot
    2.14
    т
    1.54
    ak
    1.48
    स
    1.44
     É
    1.42
    ColorEffects
    1.39
    ﻄ
    1.38
    澍
    1.35
    𝗩
    1.34
    ovány
    1.33
    POSITIVE LOGITS
    骼
    2.06
    ர்
    1.45
    ્સ
    1.40
    nz
    1.33
    normalize
    1.31
    ির
    1.27
     Slight
    1.26
    fledged
    1.25
    rzez
    1.25
    ل
    1.25
    Activations Density 0.105%

    No Known Activations