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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 83693
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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_31_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
     Banc
    0.40
     Sino
    0.40
     Nat
    0.38
    考验
    0.37
    !"));
    0.37
    itth
    0.37
     Thomas
    0.37
    停车
    0.37
     मींस
    0.37
     Philadelphia
    0.36
    POSITIVE LOGITS
    ೇಯ
    0.41
    DEVICE
    0.40
     divergence
    0.39
     ambiguity
    0.39
     *)$
    0.38
     fragment
    0.38
     twitter
    0.38
     cun
    0.38
    гули
    0.38
    ិ
    0.38
    Activations Density 0.024%

    No Known Activations