© 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. 43593
    Prev
    Next
    INDEX
    Explanations

    religious texts and prayer

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

    suffering and wounds

    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
     ridiculous
    0.41
    য়ং
    0.40
    akukan
    0.40
    magic
    0.39
    anton
    0.39
    p
    0.39
    abolic
    0.39
     dehydration
    0.39
    ukasz
    0.39
    ɑ
    0.38
    POSITIVE LOGITS
     predominant
    0.43
     உள்
    0.40
    ᱲ
    0.40
     birch
    0.39
     intuitively
    0.38
     algu
    0.37
    fireplace
    0.37
     coldest
    0.36
     effectually
    0.36
    زين
    0.36
    Activations Density 0.007%

    No Known Activations