© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8772
    Prev
    Next
    INDEX
    Explanations

    -ish endings

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

    sounds of impact and friction

    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
     Seitz
    0.47
     lifeboat
    0.47
     cicat
    0.44
     Socrates
    0.44
    珼
    0.43
     Scanner
    0.43
    皐
    0.42
     Screw
    0.41
     Chaucer
    0.41
    
    0.41
    POSITIVE LOGITS
    Ish
    2.34
    osh
    2.30
    Josh
    2.30
    ush
    2.28
     Josh
    2.25
    ISH
    2.22
    USH
    2.22
     Ish
    2.19
     ish
    2.16
    ish
    2.11
    Activations Density 0.198%

    No Known Activations