© 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. 133535
    Prev
    Next
    INDEX
    Explanations

    stories, business, summer

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

    acts but person

    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
    واج
    0.45
    اق
    0.44
    idency
    0.44
     subsistence
    0.44
    <0xB4>
    0.42
     fulfilling
    0.42
    1
    0.41
     }{\
    0.41
    emptive
    0.41
    дия
    0.40
    POSITIVE LOGITS
     Bitter
    0.49
    ienten
    0.48
     ešte
    0.47
    Afghan
    0.47
    Bitter
    0.47
     tattha
    0.45
     với
    0.45
     Rate
    0.45
     সন্ধ্যার
    0.44
     خون
    0.44
    Activations Density 0.001%

    No Known Activations