© 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. 11278
    Prev
    Next
    INDEX
    Explanations

    efficiency discussions

    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
    ﺷ
    1.76
    ✶
    1.74
     MDP
    1.71
    ﻔ
    1.70
    ជ្រ
    1.66
    <0x93>
    1.66
    KeyboardButton
    1.65
    ∋
    1.65
    塊
    1.65
     साइज
    1.65
    POSITIVE LOGITS
    eris
    1.36
    estries
    1.27
    ㄣ
    1.25
    enthal
    1.24
    туре
    1.23
    ため
    1.23
     the
    1.21
    rests
    1.21
    ын
    1.20
    andır
    1.19
    Activations Density 0.062%

    No Known Activations