© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 20325
    Prev
    Next
    INDEX
    Explanations

    expands to

    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
    use
    0.64
    ty
    0.55
    t
    0.52
    taste
    0.51
    cellular
    0.51
    MP
    0.48
    role
    0.47
    existing
    0.47
    then
    0.47
    p
    0.47
    POSITIVE LOGITS
     magia
    0.54
     Medicina
    0.52
     FaceTime
    0.49
     devad
    0.49
     obnov
    0.49
     mage
    0.48
     bén
    0.47
     Ș
    0.47
     Tumblr
    0.47
     wonderland
    0.46
    Activations Density 0.001%

    No Known Activations