© 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. 40-GEMMASCOPE-2-RES-65K
    7. 728
    Prev
    Next
    INDEX
    Explanations

    certainty

    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_40_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
     enshrined
    0.49
    Update
    0.46
     documentaries
    0.46
    Context
    0.45
    chats
    0.45
     Фургала
    0.44
    ફ
    0.43
     ethical
    0.42
    Conte
    0.42
    ల
    0.42
    POSITIVE LOGITS
     temperatur
    0.49
     complet
    0.48
     músc
    0.48
     TEMPERATURE
    0.47
     리그
    0.47
     สมการ
    0.46
     habrá
    0.45
    ertung
    0.45
     perubahan
    0.45
     तापमान
    0.44
    Activations Density 0.000%

    No Known Activations