© 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. 200728
    Prev
    Next
    INDEX
    Explanations

    advisory basis, appetite suppression, cybercrime

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

    specific context

    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
    ▇
    0.49
    ებები
    0.46
     características
    0.46
    #__
    0.46
     faç
    0.46
    }_{-}\
    0.45
    草原
    0.44
    NCIA
    0.44
    })_{\
    0.43
    ավոր
    0.43
    POSITIVE LOGITS
     Weed
    0.49
     Quad
    0.46
     Productivity
    0.41
     Scrooge
    0.41
     Demand
    0.40
     Future
    0.40
     Shore
    0.40
     Consumer
    0.39
     Becker
    0.39
     necesit
    0.39
    Activations Density 0.002%

    No Known Activations