Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8200
    Prev
    Next
    INDEX
    Explanations

    application process

    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
    이었
    0.90
    ,
    0.90
     glutamate
    0.87
    鐧
    0.86
    博物馆
    0.86
     bilirubin
    0.85
    ],
    0.85
    ،
    0.85
     происходит
    0.84
    POSITIVE LOGITS
    на
    0.91
    ून
    0.75
     Candidates
    0.69
     ).
    0.66
    ung
    0.65
     If
    0.65
    ands
    0.65
    িং
    0.65
     Be
    0.64
     Celsius
    0.63
    Activations Density 0.061%

    No Known Activations