© 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-262K
    7. 3882
    Prev
    Next
    INDEX
    Explanations

    duration or time span

    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
     vineyard
    0.95
    对
    0.78
     vineyards
    0.76
     amené
    0.76
     amélior
    0.75
     turbulence
    0.75
     ropes
    0.75
     şart
    0.74
    有两种
    0.73
    probe
    0.72
    POSITIVE LOGITS
    aaaa
    1.16
    0
    1.13
    Tidak
    1.04
    :"",
    1.04
    م
    1.04
    :
    1.03
    aaaaaaaa
    1.02
     सामान्य
    0.97
    6
    0.97
    aan
    0.96
    Activations Density 0.000%

    No Known Activations