© 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. 36190
    Prev
    Next
    INDEX
    Explanations

    trip or stumble

    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
    ेशन
    2.30
    ্দ
    2.09
     cuticle
    2.02
    ים
    1.91
    ை
    1.91
    ру
    1.89
    SizeMode
    1.86
     lymphoblastic
    1.82
     outlier
    1.81
     cytoskeleton
    1.81
    POSITIVE LOGITS
     basada
    2.14
    er
    2.03
    á
    2.03
    ur
    1.99
    ag
    1.97
    ح
    1.94
    r
    1.93
     específicos
    1.89
    ik
    1.88
     externos
    1.88
    Activations Density 0.022%

    No Known Activations