© 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. 227231
    Prev
    Next
    INDEX
    Explanations

    employers to benefits

    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
     Autonomous
    0.44
    []
    0.41
     uji
    0.41
    ’
    0.40
    ostomy
    0.40
     autonom
    0.40
     Extend
    0.40
     pronunciation
    0.39
     wn
    0.39
     homeomorphism
    0.39
    POSITIVE LOGITS
    categorie
    0.55
    ຜະລິດຕ
    0.55
    颏
    0.52
    稦
    0.50
    <unused2199>
    0.50
    <unused490>
    0.50
    <unused975>
    0.50
    devil
    0.49
    珬
    0.49
     animais
    0.49
    Activations Density 0.001%

    No Known Activations