© 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. 218509
    Prev
    Next
    INDEX
    Explanations

    employers advertise

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

    grimdark science fiction

    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
    窓
    0.55
    債
    0.50
    쓴
    0.49
    ிகள்
    0.49
     waisted
    0.49
     Drawable
    0.48
     добав
    0.46
    عدد
    0.45
    杆
    0.45
     moulded
    0.45
    POSITIVE LOGITS
     რაც
    0.51
     നിങ്ങൾക്ക്
    0.49
    es
    0.46
    ulations
    0.46
    yección
    0.46
    \}\
    0.46
     acaba
    0.46
    Antonio
    0.46
    zyła
    0.45
     দলটি
    0.44
    Activations Density 0.000%

    No Known Activations