© 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. 58143
    Prev
    Next
    INDEX
    Explanations

    the island, an ocean

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

    who or what

    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
    펨
    0.46
    యన్
    0.45
    pt
    0.44
    ᱛ
    0.44
     tumeur
    0.44
    偶然
    0.44
    ྥ
    0.44
     በሽታ
    0.43
    פט
    0.43
    ят
    0.43
    POSITIVE LOGITS
     fortes
    0.50
    Buscar
    0.47
    Những
    0.45
    ീകരണ
    0.44
    ळ्या
    0.44
     brushed
    0.44
     ragazze
    0.43
    Quantidade
    0.43
    ฮ
    0.43
    षण
    0.42
    Activations Density 0.000%

    No Known Activations