© 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. 12882
    Prev
    Next
    INDEX
    Explanations

    partially qualifying or limiting subsequent text

    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
    3
    1.59
    9
    1.53
    8
    1.53
    5
    1.52
    7
    1.46
    z
    1.45
    6
    1.41
    2
    1.36
    4
    1.33
    1
    1.25
    POSITIVE LOGITS
     които
    1.21
    šću
    1.05
    OR
    0.99
    ITUDE
    0.99
    ANDE
    0.97
    AN
    0.96
    ieť
    0.96
    owaniu
    0.95
    ependence
    0.94
    Ａ
    0.94
    Activations Density 0.069%

    No Known Activations