© 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-262K
    7. 39958
    Prev
    Next
    INDEX
    Explanations

    making decisions and moving

    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_262k_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
     реб
    0.48
    during
    0.48
    лення
    0.48
    Parliament
    0.47
    lais
    0.44
    ै
    0.44
    Unfortunately
    0.43
    Seoul
    0.43
    Manip
    0.43
    ि
    0.42
    POSITIVE LOGITS
     ke
    0.54
     titles
    0.48
    ዃ
    0.48
     targets
    0.46
     floats
    0.46
     barbers
    0.45
     f
    0.44
     imitating
    0.44
     garr
    0.44
     Targets
    0.43
    Activations Density 0.001%

    No Known Activations