© 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. 73423
    Prev
    Next
    INDEX
    Explanations

    games and strategy

    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
     were
    -1.20
     realmente
    -1.16
     encontrar
    -1.15
    на
    -1.13
     réfrig
    -1.12
    </h3>
    -1.11
     chronicle
    -1.09
     perché
    -1.09
    Now
    -1.09
    𝙪
    -1.08
    POSITIVE LOGITS
    Nicaragua
    1.23
    Venezuela
    1.23
    </h1>
    1.16
    Ţ
    1.13
    Potatoes
    1.13
     Smash
    1.13
    </b>
    1.11
    浿
    1.10
    dalam
    1.09
     Candidate
    1.09
    Activations Density 0.007%

    No Known Activations