© 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-262K
    4. 200047
    Prev
    Next
    INDEX
    Explanations

    introducing a breakdown

    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
     Each
    0.45
     ADHD
    0.41
    แต่ละ
    0.41
     etc
    0.40
     Voici
    0.40
     besch
    0.40
    \
    0.40
    ↵
    0.40
     Besch
    0.39
    মন্ত্রী
    0.39
    POSITIVE LOGITS
    :@"
    0.48
    CurrentImage
    0.44
    :...
    0.44
    :'.
    0.43
    :'
    0.42
    :[/
    0.42
    Probit
    0.40
    াঃ
    0.40
    SelfPermission
    0.39
    বৃদ্ধি
    0.39
    Activations Density 0.074%

    No Known Activations