© 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. 52510
    Prev
    Next
    INDEX
    Explanations

    YouTube video links

    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
     निगरानी
    0.52
     surveillance
    0.50
     Prote
    0.49
     guarding
    0.49
     Shaun
    0.47
    佉
    0.47
     monitoring
    0.46
     Predators
    0.45
     observing
    0.44
     guardian
    0.44
    POSITIVE LOGITS
    OFFSET
    0.43
    builtin
    0.42
    setminus
    0.42
    用到
    0.41
    цин
    0.40
    เท้า
    0.40
    Ｖ
    0.39
    ֻ
    0.39
     Ländern
    0.38
    LENGTH
    0.38
    Activations Density 0.001%

    No Known Activations