© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 132734
    Prev
    Next
    INDEX
    Explanations

    understand that

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

    clean surface

    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
    '$,
    0.47
    ในการ
    0.44
     qí
    0.42
     στην
    0.41
     کورٹ
    0.41
    OfMonth
    0.40
    以
    0.40
    `/
    0.39
     scrimmage
    0.39
    "/
    0.38
    POSITIVE LOGITS
     اوس
    0.52
    awas
    0.50
    zés
    0.47
     Ε
    0.46
    elés
    0.46
     Α
    0.46
     A
    0.45
     約
    0.45
     Antes
    0.45
     ऑगस्ट
    0.45
    Activations Density 0.000%

    No Known Activations