© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11140
    Prev
    Next
    INDEX
    Explanations

    frozen food items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    m
    2.16
    g
    2.08
    cock
    2.01
    thesis
    1.91
     ډول
    1.88
    toff
    1.84
     Imp
    1.82
    ↵
    1.82
    sig
    1.73
     attributed
    1.73
    POSITIVE LOGITS
    晫
    2.45
    鍝
    2.43
     tisu
    2.32
    нэт
    2.29
    ො
    2.22
    ેલી
    2.19
    ādi
    2.17
    𝒑
    2.17
    瀵
    2.16
    𝒆
    2.16
    Activations Density 0.008%

    No Known Activations