© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15412
    Prev
    Next
    INDEX
    Explanations

    largely followed by qualifier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    းက
    -2.63
    旰
    -2.55
    戆
    -2.48
    ﻂ
    -2.45
    珖
    -2.30
    ⸒
    -2.30
    ꜆
    -2.20
    壜
    -2.19
    琹
    -2.19
     semblable
    -2.19
    POSITIVE LOGITS
    f
    2.84
    8
    2.44
    re
    2.41
    b
    2.36
    '
    2.34
    但她
    2.31
    話は
    2.30
    鹮
    2.27
    ing
    2.17
    ت
    2.11
    Activations Density 0.005%

    No Known Activations