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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 1760
    Prev
    Next
    INDEX
    Explanations

    Shoestring Benny

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

    character descriptions and specific styles

    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
    ‐
    0.43
     transport
    0.39
     unmittelbar
    0.37
     termini
    0.36
    此前
    0.35
     наиболее
    0.35
    approx
    0.35
    ldg
    0.35
    뗀
    0.34
    prevent
    0.34
    POSITIVE LOGITS
     badass
    0.64
     foodie
    0.63
     nerdy
    0.60
     sassy
    0.59
     Fuck
    0.58
     girly
    0.58
     nerd
    0.54
     shitty
    0.54
     asshole
    0.54
     bitch
    0.53
    Activations Density 0.096%

    No Known Activations