© 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. 13050
    Prev
    Next
    INDEX
    Explanations

    sten, en, den, umen

    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
    től
    3.53
    t
    3.11
    gruppe
    2.97
    to
    2.73
    tener
    2.67
    tone
    2.66
    town
    2.64
    tight
    2.61
    tie
    2.59
    tag
    2.55
    POSITIVE LOGITS
    на
    2.94
    न
    2.73
    데요
    2.52
    율
    2.47
    ва
    2.39
    lardan
    2.38
    ان
    2.27
    ことにより
    2.27
    م
    2.25
    ہیں
    2.19
    Activations Density 0.292%

    No Known Activations