© 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
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 4574
    Prev
    Next
    INDEX
    Explanations

    which is

    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_24_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
    -
    0.44
    s
    0.42
     the
    0.41
    .'
    0.39
    0
    0.39
    0.38
    .,
    0.38
    '.
    0.37
    0.37
     gaze
    0.36
    POSITIVE LOGITS
     Tatsache
    0.57
    也就是说
    0.56
     bedeutet
    0.53
     innebär
    0.49
     betekent
    0.49
    意味着
    0.49
     Özellikle
    0.47
     evident
    0.46
    रावट
    0.45
     demek
    0.45
    Activations Density 0.008%

    No Known Activations