© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 93283
    Prev
    Next
    INDEX
    Explanations

    he she his you followed by actions

    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
    hatenablog
    -1.21
     увлаж
    -1.20
    Inoltre
    -1.09
     situato
    -1.05
     $(\%)$
    -1.05
    етесь
    -1.03
    ributing
    -0.99
    Assad
    -0.98
    ども
    -0.98
     Inoltre
    -0.96
    POSITIVE LOGITS
     my
    1.59
    ,
    1.18
     девя
    1.05
    vaných
    0.99
    pics
    0.99
     mine
    0.99
     мной
    0.98
    ⩽
    0.98
     messages
    0.98
     I
    0.96
    Activations Density 0.049%

    No Known Activations