© 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. 11352
    Prev
    Next
    INDEX
    Explanations

    security reasons and concerns

    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
    a
    3.80
    o
    3.72
    y
    3.38
    <bos>
    3.26
    en
    3.19
    ه
    2.95
    e
    2.94
    i
    2.94
    oof
    2.89
    aing
    2.88
    POSITIVE LOGITS
    ns
    2.46
    tty
    2.39
    anske
    2.36
    koľ
    2.26
    ﻯ
    2.22
    ty
    2.20
    nga
    2.19
    nya
    2.18
    𝘁
    2.17
    ties
    2.16
    Activations Density 0.420%

    No Known Activations