© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 10556
    Prev
    Next
    INDEX
    Explanations

    cannot and will not

    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
    epsilon
    0.44
     needs
    0.44
     can
    0.43
     has
    0.43
    candidate
    0.43
    Ž
    0.42
    ass
    0.41
    has
    0.41
    R
    0.41
    P
    0.41
    POSITIVE LOGITS
     لە
    0.50
     用于
    0.48
     برای
    0.47
     دوسری
    0.45
    untuk
    0.44
     şark
    0.44
    转向
    0.43
     东
    0.43
    ቝ
    0.43
     alternating
    0.42
    Activations Density 0.018%

    No Known Activations