© 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. 99944
    Prev
    Next
    INDEX
    Explanations

    predictive value F1

    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
     století
    -1.22
     réal
    -1.22
     matar
    -1.20
    }
    -1.20
    ”،
    -1.19
    优化
    -1.19
    銥
    -1.17
     initiating
    -1.16
     livs
    -1.16
     fernando
    -1.15
    POSITIVE LOGITS
     recoge
    1.30
     exatamente
    1.29
     иннова
    1.23
     into
    1.20
     I
    1.15
     constituye
    1.13
     muitos
    1.12
     justamente
    1.12
     Paramètres
    1.11
     muitas
    1.09
    Activations Density 0.022%

    No Known Activations