© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65894
    Prev
    Next
    INDEX
    Explanations

    names starting with "Ber" or "Bur"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    หรือ
    -2.27
    และ
    -2.17
     alebo
    -2.14
     they
    -2.14
    $};
    -2.11
     destinos
    -2.06
     یا
    -2.05
     continuar
    -2.05
     favoritos
    -2.03
    或者是
    -2.03
    POSITIVE LOGITS
    3
    3.45
    9
    3.08
    When
    2.75
    $,
    2.58
    6
    2.48
    While
    2.47
    1
    2.47
    Despite
    2.45
    With
    2.44
     一九
    2.44
    Activations Density 0.025%

    No Known Activations