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

    Neuronpedia

    Jacobian LensNEW
    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. 7450
    Prev
    Next
    INDEX
    Explanations

    . It

    np_acts-logits-general · gemini-2.5-flash-lite

    English contractions that use apostrophes (negations and pronoun+auxiliary verb shortenings).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
    。”
    0.43
    $\,.
    0.41
    》。
    0.38
    。",
    0.37
     pyridine
    0.35
    netHex
    0.35
    。"
    0.35
     monomials
    0.34
     آئے
    0.33
    .",[
    0.33
    POSITIVE LOGITS
    以下の
    0.41
    and
    0.40
    K
    0.40
    *
    0.40
     Pot
    0.37
     K
    0.37
    E
    0.36
    1
    0.36
    Beyond
    0.35
    Firstly
    0.35
    Activations Density 1.190%

    No Known Activations