© 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. 116166
    Prev
    Next
    INDEX
    Explanations

    knew him/her/loved

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

    Listening and learning

    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
     Spotlight
    0.55
     Insights
    0.49
     Stories
    0.48
     Representations
    0.48
     Categories
    0.47
     Wipe
    0.47
     Awards
    0.47
    জ
    0.46
     Credits
    0.46
     或者
    0.46
    POSITIVE LOGITS
    watched
    0.51
     peuple
    0.50
    셍
    0.50
    illerie
    0.48
    soever
    0.48
    chu
    0.47
    abt
    0.46
    oubt
    0.46
    holtz
    0.45
    fought
    0.45
    Activations Density 0.002%

    No Known Activations