© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 241480
    Prev
    Next
    INDEX
    Explanations

    numbers followed by text

    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
    1
    0.59
    １
    0.50
    
    0.50
    {(
    0.49
    Когда
    0.48
    膂
    0.47
     Belief
    0.47
    ⑴
    0.46
     önce
    0.46
     Abroad
    0.46
    POSITIVE LOGITS
    .
    0.76
    ,
    0.58
    )
    0.56
     asigur
    0.50
     submersible
    0.49
     postulate
    0.48
    .?
    0.48
     chromospheres
    0.48
     microturbulence
    0.48
     concom
    0.48
    Activations Density 0.011%

    No Known Activations