© 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-65K
    7. 396
    Prev
    Next
    INDEX
    Explanations

    code blocks for bash, rap, regex, email

    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_65k_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
     bleaching
    0.35
     (
    0.33
     taxonomic
    0.33
     to
    0.33
     drainage
    0.31
     spore
    0.31
     denture
    0.31
     quantification
    0.30
     singularities
    0.30
     pollutants
    0.30
    POSITIVE LOGITS
    ه
    0.40
    ي
    0.40
    https
    0.39
    ת
    0.37
    י
    0.37
    ä
    0.35
    ри
    0.34
    a
    0.33
    ट
    0.33
    კ
    0.33
    Activations Density 0.269%

    No Known Activations