© 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. 56040
    Prev
    Next
    INDEX
    Explanations

    positive word endings

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

    privacy setting, fiercely loyal, deeper into, content from

    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
    Zaw
    0.49
    ometrics
    0.45
    MET
    0.44
    Editorial
    0.44
    CapsLock
    0.44
    TITLE
    0.43
    #-
    0.42
    RET
    0.42
    OMIC
    0.42
    %:
    0.41
    POSITIVE LOGITS
     Costco
    0.48
     Prez
    0.48
     Warwickshire
    0.48
     flamboyant
    0.45
     ricco
    0.45
     Company
    0.45
     hectare
    0.45
     Gough
    0.44
     ይህም
    0.44
     Gloucestershire
    0.43
    Activations Density 0.000%

    No Known Activations