© 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. 36149
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    0.44
     o
    0.37
     classic
    0.37
    ↵
    0.36
     mel
    0.36
     classically
    0.35
     scl
    0.34
     is
    0.34
     all
    0.34
     g
    0.32
    POSITIVE LOGITS
    раб
    0.46
    kében
    0.45
     మరియు
    0.44
    eraient
    0.43
    сто
    0.43
    во
    0.42
    әт
    0.42
    ър
    0.42
     случаях
    0.42
    წი
    0.42
    Activations Density 0.266%

    No Known Activations