© 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. 71896
    Prev
    Next
    INDEX
    Explanations

    opportunity, personal loan, glittering paint

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

    max, maxed, options, pickup

    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
     vários
    0.55
     métodos
    0.55
     método
    0.52
     início
    0.52
     wiele
    0.52
    笕
    0.51
     équ
    0.50
     anál
    0.50
     itinéraires
    0.50
    ἲ
    0.50
    POSITIVE LOGITS
    ute
    0.51
    러
    0.51
    ser
    0.50
    2
    0.48
    5
    0.47
    wer
    0.46
    0
    0.46
     〢
    0.45
    uk
    0.44
    <eos>
    0.43
    Activations Density 0.001%

    No Known Activations