© 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. 16-GEMMASCOPE-2-RES-65K
    7. 262
    Prev
    Next
    INDEX
    Explanations

    if someone needed

    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_16_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
    u
    0.47
    ي
    0.34
    y
    0.34
    τητας
    0.33
    ματα
    0.31
     camels
    0.31
    er
    0.30
    ですが
    0.30
    தி
    0.30
    드는
    0.30
    POSITIVE LOGITS
     I
    0.41
    I
    0.37
     घ्या
    0.35
    um
    0.35
    be
    0.35
    ara
    0.35
    ama
    0.34
    aki
    0.33
    ,"
    0.32
    ika
    0.32
    Activations Density 0.872%

    No Known Activations