© 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. 5379
    Prev
    Next
    INDEX
    Explanations

    long time ago or long flowing

    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
    ار
    1.89
    ર
    1.89
    cracker
    1.84
    ្នុង
    1.82
    ات
    1.71
    şim
    1.70
    ре
    1.67
    十足
    1.67
    א
    1.67
    ॉ
    1.66
    POSITIVE LOGITS
    parseLong
    2.53
    ق
    1.92
    ни
    1.84
     그래도
    1.65
    hips
    1.62
    haired
    1.62
    afstand
    1.62
    favorites
    1.61
     wheelbase
    1.61
     זמן
    1.61
    Activations Density 0.093%

    No Known Activations