© 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. 217724
    Prev
    Next
    INDEX
    Explanations

    inner doors, postal address, economic challenges

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

    archive filesetsownershipsecretlyball break

    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
    হইবে
    0.45
    である
    0.45
    eze
    0.43
     domani
    0.42
    ਯ
    0.42
     obtenu
    0.42
    ともに
    0.42
     canadian
    0.42
     potrivit
    0.42
     a
    0.41
    POSITIVE LOGITS
     scintillation
    0.49
     MODE
    0.46
     CaCO
    0.46
     सोडा
    0.46
    UGG
    0.46
     мобиль
    0.45
    BOSE
    0.45
     тяже
    0.45
     состоянии
    0.45
    ococcus
    0.44
    Activations Density 0.000%

    No Known Activations