© 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. 8908
    Prev
    Next
    INDEX
    Explanations

    training and education

    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
    مه
    0.82
    در
    0.79
    ાવ
    0.75
    0.74
     அல்ல
    0.73
     communities
    0.72
     magnétique
    0.70
    서
    0.70
     surroundings
    0.69
     apr
    0.69
    POSITIVE LOGITS
    creates
    0.98
    сны
    0.95
    ⊟
    0.93
    criar
    0.92
    abá
    0.91
    ▦
    0.91
    creating
    0.87
    frameN
    0.86
    식회사
    0.86
    čka
    0.84
    Activations Density 0.001%

    No Known Activations