© 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. 15161
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and care

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

    closings like thanks or best

    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
     entsprechende
    0.37
     સરકાર
    0.35
     राजकीय
    0.35
     VGA
    0.33
     CRF
    0.33
    !!!!!!!!!!!!!!!!
    0.33
    !!!!!!!!
    0.33
    ()!=
    0.33
    !='')
    0.33
     Homemade
    0.32
    POSITIVE LOGITS
    ἔ
    0.36
    ้ำ
    0.35
    ↵
    0.35
     deliciously
    0.34
    ፣
    0.34
    続ける
    0.34
    ,—
    0.33
    >,
    0.32
     fascinating
    0.32
    électricité
    0.32
    Activations Density 0.016%

    No Known Activations