© 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. 106029
    Prev
    Next
    INDEX
    Explanations

    without recycling; needed a; inexpensive security

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

    access to information

    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
     प्रव
    0.55
     Andhra
    0.42
     अगस्त
    0.42
     승
    0.42
    inset
    0.41
    Ტ
    0.41
     settlers
    0.41
    tj
    0.41
    ☃
    0.41
    iasis
    0.41
    POSITIVE LOGITS
     biometric
    0.48
     biomarker
    0.45
     tissue
    0.44
     democracies
    0.44
     photoelectron
    0.44
     proactively
    0.44
    ོ་
    0.43
     vetro
    0.43
    नीचर
    0.43
     spectrometer
    0.43
    Activations Density 0.001%

    No Known Activations