© 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. 99477
    Prev
    Next
    INDEX
    Explanations

    flow and its context

    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
    </h1>
    -2.70
    あっという間に
    -2.58
    C
    -2.39
    that
    -2.31
    曾在
    -2.20
    ことから
    -2.17
    H
    -2.17
    ist
    -2.17
    section
    -2.11
    終わ
    -2.09
    POSITIVE LOGITS
    </em>
    2.84
    ]
    2.75
     If
    2.50
    ꜄
    2.45
     esteemed
    2.44
    𐄁
    2.38
    ранее
    2.36
    celular
    2.28
    งิน
    2.23
    了我
    2.20
    Activations Density 0.023%

    No Known Activations