© 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. 76796
    Prev
    Next
    INDEX
    Explanations

    meanshavesaves

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

    project parent dependencies

    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
     існу
    0.52
     подклю
    0.48
     ఉన్నాయి
    0.47
    ிர
    0.46
     क्वाड्र
    0.46
    {``
    0.46
    +},
    0.45
    杫
    0.45
     іх
    0.44
     существо
    0.44
    POSITIVE LOGITS
     disappointing
    0.47
     disappoint
    0.44
     porcelain
    0.43
    ζο
    0.43
     midfield
    0.43
    取
    0.42
    जिद
    0.42
    خدام
    0.41
     far
    0.41
     disappointment
    0.41
    Activations Density 0.000%

    No Known Activations