© 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. 95075
    Prev
    Next
    INDEX
    Explanations

    processing and updating data

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

    maximizing positive experiences

    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
     imped
    0.51
     inhibits
    0.50
     inhibiting
    0.49
     inflamed
    0.49
     prevents
    0.48
     није
    0.48
    诟
    0.47
    жении
    0.47
     стимули
    0.47
     মিন
    0.46
    POSITIVE LOGITS
    stars
    0.48
    adi
    0.47
    fresh
    0.46
     I
    0.46
    oo
    0.46
    ag
    0.45
    Se
    0.45
    fields
    0.45
     Reflection
    0.44
    ili
    0.44
    Activations Density 0.000%

    No Known Activations