© 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. 10-GEMMASCOPE-RES-131K
    7. 14642
    Prev
    Next
    INDEX
    Explanations

    She followed by verbs

    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_10/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
    the
    -3.05
     of
    -2.77
    to
    -2.55
    s
    -2.45
    $
    -2.42
    6
    -2.36
    b
    -2.33
    ”
    -2.19
    。"
    -2.03
     they
    -2.02
    POSITIVE LOGITS
    笮
    2.33
    Krank
    2.31
    诓
    2.19
     plong
    2.09
    を作って
    2.06
    閦
    2.06
    饜
    2.03
    )]
    2.00
    
    2.00
     которы
    1.99
    Activations Density 0.014%

    No Known Activations