© 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. 159146
    Prev
    Next
    INDEX
    Explanations

    awareness, relationships, fundraiser, facility, router

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

    explaining specific concepts like distances or representations

    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
    in
    0.49
    newer
    0.44
    ↵↵
    0.44
    er
    0.44
    inati
    0.44
    ?
    0.44
     teh
    0.43
    tre
    0.41
    če
    0.41
    burger
    0.41
    POSITIVE LOGITS
     procédé
    0.46
    يد
    0.46
     lẽ
    0.46
     estremamente
    0.45
    وبي
    0.45
    縝
    0.44
    နေရာ
    0.44
    ệc
    0.44
     đấu
    0.43
     squadre
    0.43
    Activations Density 0.001%

    No Known Activations