© 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. 238901
    Prev
    Next
    INDEX
    Explanations

    describing current or past states

    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
    神経
    0.42
     변
    0.40
     eval
    0.40
     hö
    0.40
     víctima
    0.40
     빠
    0.40
     సంద
    0.40
    ਾਰੇ
    0.40
     sensorial
    0.39
    പോ
    0.38
    POSITIVE LOGITS
    decyd
    0.48
     wielu
    0.44
     Bridal
    0.42
     nahezu
    0.42
    шинство
    0.42
    ^{*},
    0.41
     &
    0.40
     Payroll
    0.40
    udra
    0.40
    anamo
    0.40
    Activations Density 0.000%

    No Known Activations