© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 151362
    Prev
    Next
    INDEX
    Explanations

    altar, decided, diseases, session, headed, named

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

    incest and incestuous themes

    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
    Howard
    0.49
    I
    0.47
     fisheries
    0.46
    Camb
    0.45
     banker
    0.42
     stability
    0.42
     hydraulic
    0.42
     Howard
    0.41
     gdy
    0.41
     notation
    0.40
    POSITIVE LOGITS
     производителей
    0.53
    ა
    0.51
     κο
    0.49
     folhas
    0.48
    blusa
    0.48
     ارسال
    0.48
     Vậy
    0.47
     اولین
    0.47
     המו
    0.47
     дороже
    0.47
    Activations Density 0.000%

    No Known Activations