© 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. 76224
    Prev
    Next
    INDEX
    Explanations

    common skills, roofing, birth, recorded, tooth

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

    descriptive metrics and factors

    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
     worked
    0.51
     rely
    0.50
     stopped
    0.50
     concatenate
    0.50
     _
    0.49
    _
    0.49
     cps
    0.49
     fully
    0.47
     studente
    0.47
     adopt
    0.47
    POSITIVE LOGITS
    報
    0.52
    Osaka
    0.50
    兵庫
    0.48
    Mord
    0.47
     改
    0.46
     書い
    0.46
     કરવાનું
    0.45
     Livraison
    0.44
    Estos
    0.43
     पार्टियों
    0.43
    Activations Density 0.000%

    No Known Activations