© 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-262K
    7. 42006
    Prev
    Next
    INDEX
    Explanations

    string array

    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_262k_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
    the
    1.64
     phonons
    1.41
     the
    1.39
     nutrients
    1.33
     psalm
    1.31
     propellers
    1.30
     a
    1.27
     Rupees
    1.26
     compose
    1.25
    ங்களையும்
    1.24
    POSITIVE LOGITS
    ፣
    1.67
     hingegen
    1.46
    ور
    1.43
    ،
    1.41
    ၊
    1.29
     biç
    1.27
     kennt
    1.27
    、
    1.23
    entwick
    1.22
     tę
    1.20
    Activations Density 0.000%

    No Known Activations