© 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. 30347
    Prev
    Next
    INDEX
    Explanations

    end of process or life stage

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

    biological and medical processes

    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
     लहान
    0.44
     préal
    0.43
     اطراف
    0.41
     مطرح
    0.40
    доволь
    0.40
    meme
    0.39
    с
    0.39
    春节
    0.39
     இதன்
    0.39
     fürs
    0.38
    POSITIVE LOGITS
    无论是
    0.47
     onwards
    0.42
     supernat
    0.42
    無論
    0.41
     vinegar
    0.41
     STRING
    0.41
     supernatant
    0.40
     quantile
    0.40
    ，
    0.40
     onward
    0.40
    Activations Density 0.133%

    No Known Activations