© 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. 317
    Prev
    Next
    INDEX
    Explanations

    moving up

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

    logistics and personal achievements

    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
     பொதுவாக
    0.57
    一般来说
    0.52
    观察
    0.45
     संभाव
    0.45
     потен
    0.41
     повто
    0.41
     fhould
    0.40
    ậ
    0.40
    oł
    0.40
    そもそも
    0.40
    POSITIVE LOGITS
     shipments
    0.50
     shipment
    0.50
     brag
    0.49
     grandkids
    0.47
     story
    0.45
     traceability
    0.44
     logistics
    0.43
     investimentos
    0.43
     foto
    0.42
     Hitachi
    0.42
    Activations Density 0.000%

    No Known Activations