© 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. 224186
    Prev
    Next
    INDEX
    Explanations

    legal and technical terms

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

    titles and group names preceded by "The"

    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
    CONFIGURE
    0.43
    ᄐ
    0.42
    ວກ
    0.42
    кової
    0.42
    ୍ର
    0.42
    ᅭ
    0.41
    дня
    0.41
    THREADS
    0.41
    agati
    0.41
    흩
    0.41
    POSITIVE LOGITS
     gris
    0.52
     सेवानिव
    0.50
    投与
    0.47
     testicular
    0.46
     delir
    0.46
     após
    0.45
     colch
    0.45
     Playboy
    0.45
     cadáver
    0.45
     после
    0.44
    Activations Density 0.001%

    No Known Activations