© 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. 194689
    Prev
    Next
    INDEX
    Explanations

    words around common phrases

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

    positive reinforcement humane training

    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
    '
    0.51
    ’
    0.49
     readability
    0.49
     canc
    0.49
     cars
    0.48
     sieve
    0.46
     fantastic
    0.45
    ر
    0.45
     NOVA
    0.44
     Decorative
    0.44
    POSITIVE LOGITS
     выбрать
    0.52
    㤟
    0.52
    Amérique
    0.52
     ভারতীয়রা
    0.51
     éventuellement
    0.51
     wybrać
    0.51
     Amérique
    0.50
    jskiego
    0.47
     эпоху
    0.46
     जूनियर
    0.46
    Activations Density 0.000%

    No Known Activations