© 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. 94988
    Prev
    Next
    INDEX
    Explanations

    check cashing kiosks

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

    list of considerations

    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
    следование
    0.54
     భాష
    0.50
     Мари
    0.48
     시민
    0.48
    로우
    0.47
     среде
    0.47
    Manisha
    0.47
    주
    0.47
    现状
    0.47
    团结
    0.47
    POSITIVE LOGITS
     piston
    0.52
     burned
    0.50
     therein
    0.49
     respectively
    0.48
     thereof
    0.48
     anterior
    0.47
     ilus
    0.47
     respectivamente
    0.46
     assembled
    0.45
     replay
    0.45
    Activations Density 0.001%

    No Known Activations