© 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. 220296
    Prev
    Next
    INDEX
    Explanations

    events, calibrations, months, or programs

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

    logical deduction and specific vocabulary

    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
     quelques
    0.53
     Prussia
    0.50
    larından
    0.50
     paysans
    0.50
     Beziehungen
    0.49
    }=\
    0.48
    sig
    0.48
     beginnetje
    0.48
     выборах
    0.47
     étages
    0.47
    POSITIVE LOGITS
     functioning
    0.43
     lateral
    0.42
     headless
    0.42
     written
    0.41
     devices
    0.41
     boxes
    0.40
    ô
    0.40
     맡
    0.39
     “
    0.39
     net
    0.39
    Activations Density 0.000%

    No Known Activations