© 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. 1847
    Prev
    Next
    INDEX
    Explanations

    tiramisu

    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
    ות
    1.35
    Ts
    1.19
    larni
    1.10
    ње
    1.09
    u
    1.09
    Ů
    1.06
    utage
    1.03
    UR
    1.02
    ństw
    1.01
     ідэ
    1.00
    POSITIVE LOGITS
     Chronic
    1.13
    した
    1.10
    FBSDKGraph
    1.10
     PASS
    1.08
    ما
    1.05
    دو
    1.05
     должность
    1.04
    但也
    1.04
    汩
    1.04
    したら
    1.02
    Activations Density 0.001%

    No Known Activations