© 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. 92781
    Prev
    Next
    INDEX
    Explanations

    materials

    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
     purplish
    -0.86
     parf
    -0.83
     blanch
    -0.79
     blackish
    -0.79
     خودش
    -0.77
    žné
    -0.77
    NACIONAL
    -0.77
     dyeing
    -0.76
     thermomix
    -0.76
    ``,
    -0.75
    POSITIVE LOGITS
     metal
    2.70
     steel
    2.27
     plastic
    2.22
     aluminum
    2.13
     wooden
    2.11
     wood
    2.09
     stainless
    2.09
     aluminium
    2.00
    metal
    1.92
     PVC
    1.92
    Activations Density 0.305%

    No Known Activations