© 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. 195132
    Prev
    Next
    INDEX
    Explanations

    giftsage years

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

    to know

    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
    Stainless
    0.52
    Ặ
    0.52
     ARC
    0.51
    ופ
    0.46
    ري
    0.46
    פו
    0.46
    으로
    0.45
    مق
    0.44
     Stainless
    0.44
    מ
    0.44
    POSITIVE LOGITS
     তুর
    0.48
     Tsing
    0.47
     Eros
    0.45
    大规模
    0.44
     humoral
    0.43
    splitLength
    0.43
     tuttavia
    0.43
     nitrog
    0.43
     roll
    0.43
     පො
    0.43
    Activations Density 0.001%

    No Known Activations