© 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. 52678
    Prev
    Next
    INDEX
    Explanations

    common payment, attraction, conservation

    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
     deputado
    0.50
     contextos
    0.49
     বলো
    0.49
    િંગ
    0.46
     Fakat
    0.46
    磋商
    0.46
     `#
    0.45
    ান্স
    0.45
    {-#
    0.44
    aná
    0.43
    POSITIVE LOGITS
    :");
    0.43
     Percolation
    0.43
    ỏe
    0.43
     uncl
    0.41
    を聞
    0.40
     बस
    0.40
     Athlete
    0.39
    yue
    0.39
    usr
    0.38
     oppressive
    0.38
    Activations Density 0.008%

    No Known Activations