© 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. 11360
    Prev
    Next
    INDEX
    Explanations

    map

    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
    er
    3.32
    加坡
    3.15
    eris
    3.08
    𝗥
    3.03
    تها
    2.96
    توان
    2.90
    मर्रा
    2.89
    ر
    2.83
    oclonal
    2.76
     bare
    2.72
    POSITIVE LOGITS
    heit
    2.66
    ة
    2.47
    ————
    2.45
    het
    2.43
    msgSender
    2.40
    Méd
    2.36
    **************/
    2.33
    ल्पनिक
    2.31
    ahre
    2.24
    ूण
    2.23
    Activations Density 0.015%

    No Known Activations