© 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. 13715
    Prev
    Next
    INDEX
    Explanations

    cameras capture, average daytime, not violet

    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
    艘
    0.47
    DEVICE
    0.47
    ﺷ
    0.46
    ство
    0.46
     бе
    0.45
     смер
    0.45
    र्जा
    0.45
     spermato
    0.44
     देखा
    0.44
     शार
    0.43
    POSITIVE LOGITS
    manager
    0.49
    on
    0.49
    iv
    0.47
    of
    0.47
    ien
    0.43
    to
    0.41
     n
    0.40
    bags
    0.40
     Preventing
    0.40
    controller
    0.39
    Activations Density 0.058%

    No Known Activations