© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 32120
    Prev
    Next
    INDEX
    Explanations

    in its

    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
    ુ
    1.02
    iramente
    0.85
    mie
    0.85
    e
    0.84
    irs
    0.82
     lave
    0.82
    WAY
    0.81
    odore
    0.80
     появляются
    0.80
    ారు
    0.80
    POSITIVE LOGITS
     covariate
    0.85
    radiated
    0.83
     혹은
    0.83
    द्ध
    0.82
    cstring
    0.79
    
    0.78
     supervisory
    0.77
     baryon
    0.77
    ма
    0.76
    graduation
    0.76
    Activations Density 0.000%

    No Known Activations