© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 173677
    Prev
    Next
    INDEX
    Explanations

    family wall décor

    np_acts-logits-general · gemini-2.5-flash-lite

    specific instructions or business processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deriv
    0.46
     manpower
    0.45
     fingerprints
    0.43
    .,
    0.42
     labourers
    0.42
    容
    0.42
    ↵↵
    0.41
     symbolic
    0.41
     convincing
    0.40
    چر
    0.40
    POSITIVE LOGITS
     LoggerFactory
    0.52
     худо
    0.50
     син
    0.50
    uffy
    0.50
     давно
    0.49
     भाग्य
    0.49
    嗱
    0.49
    sudo
    0.48
     فراموش
    0.48
     मगर
    0.48
    Activations Density 0.002%

    No Known Activations