© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14015
    Prev
    Next
    INDEX
    Explanations

    tool for function

    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_13_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
    вает
    2.56
    𝚒
    2.54
    /-}$
    2.52
     pertes
    2.45
    ∂</
    2.43
     nở
    2.43
    ﻯ
    2.40
    ﻓ
    2.40
    ᵗ
    2.38
     ngưỡng
    2.37
    POSITIVE LOGITS
    <bos>
    3.39
    StripMenuItem
    2.74
    elez
    2.40
    eus
    2.39
    szak
    2.37
    sz
    2.34
    ా
    2.27
    此同时
    2.21
    ه
    2.19
    kennung
    2.17
    Activations Density 0.123%

    No Known Activations