© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 133578
    Prev
    Next
    INDEX
    Explanations

    locations and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite

    oil supply, tissue healing, generate marketing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :
    0.54
    प्रधानमंत्री
    0.53
    س
    0.52
     conduite
    0.51
     nationale
    0.50
    sommets
    0.49
     acuerdo
    0.49
     crescimento
    0.47
    marginBottom
    0.47
     nacional
    0.46
    POSITIVE LOGITS
     రావ
    0.52
     Abilities
    0.48
     Qualifying
    0.47
     अनन्या
    0.47
     Berikut
    0.45
     해당
    0.44
     Capabilities
    0.44
    
    0.44
     StreamWriter
    0.44
     YOU
    0.44
    Activations Density 0.001%

    No Known Activations