© 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. 34-GEMMASCOPE-RES-131K
    7. 93154
    Prev
    Next
    INDEX
    Explanations

    v followed by number

    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_34/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
    mismo
    -1.01
     attorno
    -0.90
    radan
    -0.90
     ciascuno
    -0.87
     ooit
    -0.85
     qualcuno
    -0.85
    ǧ
    -0.84
     qualunque
    -0.83
    Kör
    -0.83
    Rö
    -0.83
    POSITIVE LOGITS
    beta
    1.30
     sua
    0.88
     sociedad
    0.84
    v
    0.83
    との
    0.83
    の
    0.81
    ッド
    0.81
     beta
    0.81
    での
    0.80
     Beta
    0.79
    Activations Density 0.039%

    No Known Activations