© 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. 172603
    Prev
    Next
    INDEX
    Explanations

    standardized testing

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

    prolong, check, target

    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
     indiquer
    0.60
     ocasi
    0.56
    ଂ
    0.55
    وہ
    0.53
    શન
    0.53
    κο
    0.51
    מ
    0.51
    ﺷ
    0.51
    樁
    0.51
    :}
    0.50
    POSITIVE LOGITS
    0.60
    -
    0.55
     Power
    0.52
    ate
    0.51
    algia
    0.49
    iffer
    0.49
     Cavalry
    0.49
     root
    0.48
     Mega
    0.48
     Root
    0.47
    Activations Density 0.000%

    No Known Activations