© 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. 204111
    Prev
    Next
    INDEX
    Explanations

    providing coverages or groups

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

    assumes good intentions or positive outcomes

    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
    osi
    0.55
     ogrod
    0.52
    awara
    0.50
     utilidad
    0.48
    ಸಿದ
    0.48
    iesi
    0.47
     siti
    0.47
    朢
    0.47
    usia
    0.46
     teoría
    0.46
    POSITIVE LOGITS
     Halsey
    0.44
    CHANNEL
    0.44
     DIA
    0.44
    BufferedWriter
    0.43
    ᅲ
    0.43
     Personalized
    0.43
     aggressively
    0.41
     Palmas
    0.41
    ENANCE
    0.41
     Golds
    0.41
    Activations Density 0.001%

    No Known Activations