© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9205
    Prev
    Next
    INDEX
    Explanations

    Frank followed by a name or word

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

    names starting with "frank"

    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_40_width_16k_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
    ……….
    0.40
    _______
    0.40
    mex
    0.39
    пло
    0.39
     част
    0.38
     વાળ
    0.38
    Liên
    0.38
    ………….
    0.38
    
    0.38
    ট
    0.38
    POSITIVE LOGITS
     Sinatra
    0.65
    furter
    0.64
     frank
    0.64
    FRANK
    0.61
    frank
    0.58
    furt
    0.55
     फ्रै
    0.55
    Frank
    0.54
     Frank
    0.54
    enstein
    0.52
    Activations Density 0.058%

    No Known Activations