© 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. 64809
    Prev
    Next
    INDEX
    Explanations

    wingspan, glider, scale models

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

    vehicles, aircraft, and activities

    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
     filmmaking
    0.44
     suspensión
    0.44
    ໊
    0.44
     Inbetriebnahme
    0.44
     hảo
    0.43
    ্রী
    0.43
     शूट
    0.43
    ریشن
    0.42
    такт
    0.42
     filming
    0.42
    POSITIVE LOGITS
    ><
    0.46
    3
    0.46
     slav
    0.45
     garb
    0.44
     Week
    0.42
     كر
    0.42
     wit
    0.41
    week
    0.41
     entweder
    0.40
    cir
    0.40
    Activations Density 0.010%

    No Known Activations