Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 949
    Prev
    Next
    INDEX
    Explanations

    quantifiers or types followed by specific terms

    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
     vzděl
    0.35
     incrível
    0.33
     приез
    0.33
    <unused980>
    0.32
     izinsuku
    0.32
     لد
    0.31
     الخدم
    0.31
     نع
    0.30
     لمدة
    0.30
    dDays
    0.30
    POSITIVE LOGITS
    -
    0.52
    -,
    0.48
     or
    0.40
    或
    0.40
     (
    0.39
     horizontal
    0.38
     homogeneous
    0.37
     channel
    0.37
     или
    0.36
     side
    0.36
    Activations Density 0.092%

    No Known Activations