© 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. 88187
    Prev
    Next
    INDEX
    Explanations

    terms and conditions consent

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

    both on and off

    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
    ಹ
    0.56
    ⺈
    0.47
    为空
    0.46
     философ
    0.46
    StillWater
    0.46
    Доб
    0.45
    gebäude
    0.45
     የቀ
    0.45
    䥑
    0.45
    ƅ
    0.45
    POSITIVE LOGITS
     तीस
    0.47
     says
    0.44
     Saturday
    0.43
     Monday
    0.43
     délai
    0.42
     Sunday
    0.42
     nine
    0.41
     syndicated
    0.40
     playoffs
    0.40
     Thursday
    0.40
    Activations Density 0.002%

    No Known Activations