© 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. 129038
    Prev
    Next
    INDEX
    Explanations

    color, opacity, hover, pressed states

    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
     rootReducer
    -0.94
    undum
    -0.92
     können
    -0.87
    ּוֹ
    -0.85
    ⁹
    -0.84
    йо
    -0.83
    charges
    -0.81
     verwenden
    -0.81
     According
    -0.81
     vna
    -0.79
    POSITIVE LOGITS
    Denne
    0.94
     zwięks
    0.90
    手术
    0.90
    lloworld
    0.90
    nament
    0.90
     hovered
    0.90
    tahu
    0.89
    Ār
    0.89
    InkWell
    0.89
     dù
    0.85
    Activations Density 0.013%

    No Known Activations