© 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. 161165
    Prev
    Next
    INDEX
    Explanations

    infrared first inconvenient interface

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

    counselor or marijuana

    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
     für
    0.49
     for
    0.49
     untuk
    0.48
     to
    0.47
    au
    0.46
     για
    0.46
     TO
    0.45
     ['(?
    0.45
     для
    0.44
     برای
    0.44
    POSITIVE LOGITS
    نق
    0.48
    ៤
    0.48
    gebaut
    0.47
    теле
    0.47
    藺
    0.47
    тна
    0.46
    पहली
    0.46
    ریم
    0.46
     primeras
    0.46
     agricoles
    0.46
    Activations Density 0.000%

    No Known Activations