© 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. 59063
    Prev
    Next
    INDEX
    Explanations

    machine code or vector instructions

    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
    ten
    -1.48
    他們
    -1.35
     bancaire
    -1.34
     spécialiste
    -1.33
    ED
    -1.32
    the
    -1.30
    end
    -1.27
    繚
    -1.27
    </tr>
    -1.27
    コロナ禍
    -1.26
    POSITIVE LOGITS
     frecuentemente
    1.63
     acontecer
    1.41
     Otras
    1.34
    Cuen
    1.30
     ocorrer
    1.29
     Lengkap
    1.28
     hru
    1.27
     perfeitamente
    1.27
     traslad
    1.26
    jelly
    1.24
    Activations Density 0.004%

    No Known Activations