© 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-65K
    7. 1915
    Prev
    Next
    INDEX
    Explanations

    repetitive sounds and symbols

    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
     completions
    0.20
     bodice
    0.19
    ెల
    0.18
     deoarece
    0.18
     competenze
    0.18
     maatau
    0.18
    ᱲ
    0.18
     clé
    0.18
    িতায়
    0.18
    📊
    0.18
    POSITIVE LOGITS
    etc
    0.23
    end
    0.22
    С
    0.22
    ient
    0.21
    ா
    0.21
    无比
    0.21
    if
    0.21
    java
    0.21
    its
    0.20
    this
    0.20
    Activations Density 0.146%

    No Known Activations