© 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. 106551
    Prev
    Next
    INDEX
    Explanations

    file except in compliance

    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
     deta
    -0.90
     plausible
    -0.89
     Depor
    -0.81
     kupić
    -0.76
     ſo
    -0.76
     Vitamina
    -0.76
    mlı
    -0.75
    ᱾
    -0.75
     feasibility
    -0.74
    ที่สุด
    -0.74
    POSITIVE LOGITS
     except
    1.08
     إلا
    0.96
     project
    0.91
     unless
    0.87
    except
    0.87
     seragam
    0.87
     decât
    0.81
     or
    0.80
     piccolo
    0.78
     May
    0.77
    Activations Density 0.291%

    No Known Activations