© 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. 149431
    Prev
    Next
    INDEX
    Explanations

    phrases following specific start words

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

    casa particular, instance, Dug, boy, Volgograd, crocodile

    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
     maž
    0.50
     zewnętrzne
    0.50
     airspace
    0.46
     transmis
    0.46
    δε
    0.46
    늪
    0.46
    크
    0.45
     około
    0.44
     afară
    0.44
     assurance
    0.44
    POSITIVE LOGITS
     परिश्रम
    0.50
    懵
    0.49
     Oed
    0.47
    ▐
    0.46
     हादसे
    0.45
    arn
    0.44
     करियर
    0.44
     Medical
    0.43
    onnen
    0.43
     শাস
    0.43
    Activations Density 0.000%

    No Known Activations