© 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-262K
    7. 9363
    Prev
    Next
    INDEX
    Explanations

    laws and regulations

    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
     gême
    0.85
     prácticamente
    0.84
     vivió
    0.82
     þei
    0.81
     praticamente
    0.77
     capace
    0.77
    栘
    0.77
     cuestión
    0.77
    FROM
    0.76
     protagon
    0.76
    POSITIVE LOGITS
     and
    1.34
    y
    1.23
     a
    1.10
    n
    1.09
     is
    1.07
    i
    1.07
    s
    1.04
     in
    1.02
    3
    1.02
    2
    0.99
    Activations Density 0.319%

    No Known Activations