© 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. 115535
    Prev
    Next
    INDEX
    Explanations

    compensation policies

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

    different reference ranges

    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
     mischiev
    0.47
     സാധ്യത
    0.42
     majú
    0.41
    zinha
    0.41
     Arundel
    0.41
    缝
    0.40
     confertim
    0.40
     mají
    0.39
    <0x0D>
    0.39
     nimi
    0.39
    POSITIVE LOGITS
    اں
    0.48
     COURT
    0.46
    ò
    0.46
    STRA
    0.45
     munc
    0.45
    こうした
    0.45
    る
    0.44
    ా
    0.44
    ༈
    0.44
    RIO
    0.44
    Activations Density 0.001%

    No Known Activations