© 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. 43901
    Prev
    Next
    INDEX
    Explanations

    mayor or myself burned

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

    contextualizing information after a phrase

    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
     Elimination
    0.39
     Plus
    0.39
     maturation
    0.38
    ↵
    0.38
     digitalization
    0.37
     Void
    0.37
     Mythology
    0.37
     EMP
    0.36
     RTP
    0.36
     Wikipedia
    0.36
    POSITIVE LOGITS
    amard
    0.52
     dowol
    0.51
    ЛИ
    0.51
     ಐ
    0.50
     incluindo
    0.50
     раді
    0.50
     curled
    0.49
     ovvero
    0.49
     alebo
    0.48
     addItem
    0.48
    Activations Density 0.000%

    No Known Activations