© 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. 77691
    Prev
    Next
    INDEX
    Explanations

    comparison or evaluation

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

    Days turned, enabling me, poised to

    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
     tendered
    0.49
    esten
    0.49
    IVACON
    0.48
    یم
    0.48
     Variance
    0.48
     addons
    0.46
     Retention
    0.46
    漃
    0.46
     Advis
    0.46
    izan
    0.46
    POSITIVE LOGITS
     最大
    0.47
     blight
    0.45
    lain
    0.44
     icch
    0.44
     dripping
    0.44
     只
    0.43
     &:
    0.43
     mundane
    0.42
    затор
    0.42
     eclipse
    0.42
    Activations Density 0.000%

    No Known Activations