© 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. 10355
    Prev
    Next
    INDEX
    Explanations

    not X or be X

    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
     narrates
    1.73
    т
    1.70
    larda
    1.66
    lardan
    1.63
     что
    1.55
     ಸಲ್ಲ
    1.54
     бывает
    1.52
    которые
    1.45
     sebepler
    1.45
    lara
    1.44
    POSITIVE LOGITS
    ار
    1.76
    ות
    1.47
    ando
    1.45
    ัท
    1.38
    }(
    1.35
     heureux
    1.34
    অধ
    1.33
    redient
    1.32
     gong
    1.31
    께
    1.31
    Activations Density 0.367%

    No Known Activations