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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 3555
    Prev
    Next
    INDEX
    Explanations

    fox cub

    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
     Illness
    1.02
     '|')
    0.95
     iterates
    0.94
     Effort
    0.89
    🧉
    0.89
     Onion
    0.85
     Commun
    0.85
     ']
    0.85
     Oxid
    0.84
     ………………………………..
    0.84
    POSITIVE LOGITS
     järjest
    1.09
    ae
    1.05
    ссий
    1.02
    ье
    1.01
    ούς
    1.00
    iak
    0.98
     dyd
    0.97
    ী
    0.96
     большинство
    0.95
     vē
    0.95
    Activations Density 0.001%

    No Known Activations