© 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-16K
    7. 13744
    Prev
    Next
    INDEX
    Explanations

    qualities and characteristics

    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_16k_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
     অথচ
    0.48
     কিন্তু
    0.46
     però
    0.45
     pero
    0.44
     لكن
    0.44
     ولكن
    0.43
    雖
    0.43
     ಆದರೆ
    0.42
     mutta
    0.42
     भले
    0.42
    POSITIVE LOGITS
    对于
    0.47
     Each
    0.46
    Each
    0.45
    它
    0.44
     it
    0.44
    それは
    0.44
    Doesn
    0.44
    It
    0.43
     결국
    0.43
     ultimately
    0.42
    Activations Density 0.103%

    No Known Activations