© 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. 32598
    Prev
    Next
    INDEX
    Explanations

    future time periods

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

    graphic gay erotica

    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
     réservation
    0.50
     পাচ্ছি
    0.50
     iniziamo
    0.48
     bimod
    0.48
     protruding
    0.47
    വരുടെ
    0.46
    琚
    0.46
     Daher
    0.45
     aspirated
    0.45
     Arkadaşlar
    0.44
    POSITIVE LOGITS
    computer
    0.54
    S
    0.52
    invest
    0.44
    G
    0.44
    work
    0.42
    get
    0.42
    prog
    0.42
    sc
    0.41
     But
    0.40
    alt
    0.40
    Activations Density 0.000%

    No Known Activations