© 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. 52983
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    2
    0.28
    4
    0.27
    9
    0.26
    news
    0.26
    6
    0.25
    議員
    0.24
    7
    0.24
    5
    0.23
    3
    0.23
    1
    0.22
    POSITIVE LOGITS
     patina
    0.24
     végétaux
    0.24
     microbiota
    0.23
     matériau
    0.23
     الطعام
    0.23
     pulleys
    0.23
     terroir
    0.22
    焦虑
    0.22
     epochs
    0.22
     immersion
    0.22
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.