© 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. 174839
    Prev
    Next
    INDEX
    Explanations

    before using

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

    durability, focus

    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
     極
    0.52
    一種
    0.47
     원래
    0.46
    立场
    0.46
     DSG
    0.45
    DSC
    0.44
     ელ
    0.44
    指南
    0.43
     
    0.42
    兩
    0.42
    POSITIVE LOGITS
     photoshoot
    0.49
     населения
    0.49
     unseren
    0.48
     photographed
    0.47
     songwriters
    0.46
     murderers
    0.46
    udarstven
    0.45
    \}=
    0.44
     celeb
    0.44
     commemorated
    0.44
    Activations Density 0.001%

    No Known Activations