© 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. 5629
    Prev
    Next
    INDEX
    Explanations

    adhesive

    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
     APIDC
    0.52
     बेरोजगारी
    0.50
     humanist
    0.49
     precession
    0.49
    childComplexity
    0.48
     arrogant
    0.48
     философ
    0.47
    ⱨ
    0.46
     hatred
    0.46
     Rajya
    0.46
    POSITIVE LOGITS
     adhesive
    1.40
     adhesives
    1.21
     Adhesive
    1.20
    adhesive
    1.14
     sticky
    1.06
     adhesion
    1.04
     glue
    0.97
     Sticky
    0.95
    Sticky
    0.94
    sticky
    0.89
    Activations Density 0.034%

    No Known Activations