© 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. 165699
    Prev
    Next
    INDEX
    Explanations

    services or exercise

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

    actual surprise```pythonfor a```offering free```pythontest the```

    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
     Accordingly
    0.51
    ng
    0.49
    iri
    0.49
     छह
    0.49
    ed
    0.49
     April
    0.48
    ->
    0.47
    ée
    0.47
     Tuesday
    0.47
     Section
    0.46
    POSITIVE LOGITS
     heuristics
    0.51
    秵
    0.51
     seminars
    0.50
     simulations
    0.49
     benchmarks
    0.48
    ంచరీలు
    0.47
     exemptions
    0.46
     семина
    0.46
     extractive
    0.46
     vacancies
    0.46
    Activations Density 0.003%

    No Known Activations