© 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. 94755
    Prev
    Next
    INDEX
    Explanations

    accommodation with a kitchen

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

    key-value pairs and aliases

    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
     santi
    0.52
    []{
    0.48
     Guel
    0.45
     y
    0.44
     kir
    0.44
     Kj
    0.44
     daga
    0.42
     preceding
    0.42
     dawa
    0.42
    (&
    0.42
    POSITIVE LOGITS
    ле
    0.53
    बोल
    0.50
    orphism
    0.48
     النظر
    0.48
     यूक्रेन
    0.47
    Ukraine
    0.46
    तं
    0.46
     फ्यूचर
    0.45
    ells
    0.45
    ್ಯೂ
    0.45
    Activations Density 0.000%

    No Known Activations