© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13781
    Prev
    Next
    INDEX
    Explanations

    POS

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

    expiration

    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_16k_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
    錒
    0.48
    вався
    0.47
    導數
    0.46
     மேற்பர
    0.45
    拁
    0.45
    ğinin
    0.44
    PartResult
    0.44
    ቁ
    0.44
    ดย
    0.43
    Congressional
    0.43
    POSITIVE LOGITS
    ,
    0.56
     have
    0.48
     forward
    0.48
    >
    0.48
     Wars
    0.46
     crack
    0.46
    wars
    0.46
     punch
    0.45
     ,
    0.44
     limp
    0.44
    Activations Density 0.005%

    No Known Activations