© 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. 22-GEMMASCOPE-RES-131K
    7. 26344
    Prev
    Next
    INDEX
    Explanations

    quantity or composition

    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_22/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
     wadah
    -1.01
     two
    -0.99
    choly
    -0.91
     älteren
    -0.90
     when
    -0.89
    ፓ
    -0.85
     organisations
    -0.85
     betreffenden
    -0.84
     with
    -0.83
    elles
    -0.82
    POSITIVE LOGITS
     lahat
    1.14
     variety
    1.02
     pleaf
    1.01
     וכל
    0.93
    nadequate
    0.91
     面包
    0.90
    drawSprites
    0.90
     range
    0.89
    ことになる
    0.89
     izle
    0.88
    Activations Density 0.108%

    No Known Activations