© 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. 20716
    Prev
    Next
    INDEX
    Explanations

    infinitives

    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
     intelligence
    0.41
    Red
    0.41
     ruby
    0.40
     MS
    0.40
    国立
    0.40
     intel
    0.39
     ஒ
    0.39
    university
    0.39
     in
    0.39
     민
    0.38
    POSITIVE LOGITS
    ور
    0.57
    ون
    0.55
    )،
    0.53
    ור
    0.51
    埒
    0.48
     conceito
    0.47
    كَ
    0.46
    ঙ্ঘ
    0.45
    迳
    0.45
    новништво
    0.44
    Activations Density 0.018%

    No Known Activations