© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 60584
    Prev
    Next
    INDEX
    Explanations

    describing the shape of things

    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
    erba
    -0.81
     Fortnite
    -0.77
    menistan
    -0.77
    𝙫
    -0.75
     Belanda
    -0.75
    Fortnite
    -0.72
    ówki
    -0.70
     corrispond
    -0.69
     poète
    -0.69
     Colette
    -0.69
    POSITIVE LOGITS
     shape
    7.22
    shape
    6.13
     Shape
    5.38
    Shape
    5.34
     shapes
    4.41
    SHAPE
    4.31
     SHAPE
    4.28
    hape
    3.77
    shapes
    3.42
     Shapes
    3.36
    Activations Density 0.065%

    No Known Activations