© 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. 12782
    Prev
    Next
    INDEX
    Explanations

    representative or liaison

    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
    шению
    1.34
    ্বেও
    1.22
    𝕦
    1.20
    elés
    1.15
    시키
    1.14
    ωνα
    1.14
    ଈ
    1.14
    ributing
    1.13
    ovaniyu
    1.13
    タウン
    1.13
    POSITIVE LOGITS
    Те
    1.33
    Ти
    1.10
    в
    1.07
     )
    1.05
    Neces
    1.05
    И
    1.05
     Proxy
    1.03
    А
    1.03
    Bench
    1.02
    )
    1.02
    Activations Density 0.193%

    No Known Activations