© 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. 35749
    Prev
    Next
    INDEX
    Explanations

    political discussions and analysis

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

    care, game, printing, video

    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
     원래
    0.44
     входит
    0.44
     входят
    0.43
    濫
    0.42
    g
    0.42
     NLR
    0.41
     تشتغل
    0.41
    pR
    0.40
     XRD
    0.40
    隸
    0.39
    POSITIVE LOGITS
     erkennen
    0.49
     mee
    0.49
     gastronomic
    0.47
    linkColor
    0.46
    améliorer
    0.46
     amélior
    0.46
     entdecken
    0.44
    Paper
    0.44
     connaître
    0.44
     pape
    0.43
    Activations Density 0.000%

    No Known Activations