© 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. 63810
    Prev
    Next
    INDEX
    Explanations

    battery types and characteristics

    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
    𝒪
    -0.97
    等我
    -0.91
     obrazov
    -0.86
     sintético
    -0.83
     nástro
    -0.82
    cloudflare
    -0.81
    Boiler
    -0.81
    Computers
    -0.81
     Protestant
    -0.80
     burners
    -0.80
    POSITIVE LOGITS
     batteries
    1.73
     battery
    1.66
     lithium
    1.63
     Lithium
    1.61
     charging
    1.60
     cells
    1.57
     charge
    1.49
     Battery
    1.48
     voltage
    1.48
    charge
    1.41
    Activations Density 0.060%

    No Known Activations