© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 40669
    Prev
    Next
    INDEX
    Explanations

    directly hunted or Armin Arlert

    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
    war
    0.45
     ||
    0.44
    asting
    0.44
    ages
    0.43
    af
    0.43
    cc
    0.43
    fron
    0.43
    ired
    0.42
    agers
    0.42
    vers
    0.41
    POSITIVE LOGITS
    чами
    0.47
     Sentiment
    0.47
     grossly
    0.47
    ອບ
    0.46
    廪
    0.46
    レタン
    0.45
     Grossman
    0.45
     Coaching
    0.45
     temporarily
    0.44
     së
    0.44
    Activations Density 0.004%

    No Known Activations