© 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. 5702
    Prev
    Next
    INDEX
    Explanations

    terms and conditions

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

    domain-specific keywords and content-bearing nouns that signal the main topic or task context of a passage.

    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
     Մ
    0.28
     menacing
    0.28
    ަލ
    0.27
    ៧
    0.27
     영화
    0.27
     bruke
    0.26
     morceau
    0.25
     montrer
    0.24
     لباس
    0.24
     gruesome
    0.24
    POSITIVE LOGITS
     from
    0.28
    i
    0.27
    index
    0.25
    able
    0.24
     and
    0.24
    _
    0.23
    Q
    0.23
    state
    0.23
    q
    0.22
    from
    0.22
    Activations Density 3.224%

    No Known Activations