© 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. 4811
    Prev
    Next
    INDEX
    Explanations

    intensifiers like so, such, much

    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
    on
    1.05
    [
    0.90
     frame
    0.89
    ub
    0.86
    frame
    0.85
    Weitere
    0.84
     যতটুকু
    0.84
    un
    0.82
    Wir
    0.82
    ваты
    0.81
    POSITIVE LOGITS
    রের
    1.13
    те
    1.10
    тың
    1.06
    та
    1.05
    𝑡
    1.02
    ром
    1.02
    𝙖
    1.02
    𝙩
    1.01
    𝐭
    0.96
    সূ
    0.94
    Activations Density 0.148%

    No Known Activations