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-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 4470
    Prev
    Next
    INDEX
    Explanations

    ibid citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    ██
    0.31
     compute
    0.30
     tensor
    0.30
     tumble
    0.29
     neural
    0.28
     deu
    0.28
     monotonic
    0.28
     spline
    0.28
     PREFIX
    0.28
     supernovae
    0.27
    POSITIVE LOGITS
     ibid
    0.40
    जिस
    0.33
    S
    0.33
    Note
    0.33
    Ibid
    0.32
     ironically
    0.32
     எப்படி
    0.31
    ibid
    0.31
    今回の
    0.31
     Ibid
    0.31
    Activations Density 0.030%

    No Known Activations