© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 4081
    Prev
    Next
    INDEX
    Explanations

    male names

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

    names in closings

    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_53_width_65k_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
     xD
    0.73
     shitty
    0.65
     tbh
    0.63
     Haha
    0.58
     haha
    0.58
     Honestly
    0.57
     =)
    0.56
     fuck
    0.55
     fiance
    0.55
     :/
    0.55
    POSITIVE LOGITS
    Bob
    0.75
    Jim
    0.71
    Mike
    0.69
    Larry
    0.68
     Jim
    0.66
     Bob
    0.66
    Dave
    0.66
    Ron
    0.65
    Bill
    0.64
    Gary
    0.64
    Activations Density 0.152%

    No Known Activations