© 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. 181989
    Prev
    Next
    INDEX
    Explanations

    present tense, mention descriptions

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

    describing qualities, effects, or uses

    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
     to
    0.54
    していました
    0.54
     我們
    0.49
     フロ
    0.49
     過
    0.49
    してた
    0.49
     מפ
    0.48
    ility
    0.47
    nd
    0.47
    為
    0.46
    POSITIVE LOGITS
     एक्सप्रेस
    0.48
     IDS
    0.46
    Begriffsklär
    0.44
     wiad
    0.43
     Mule
    0.43
     инвести
    0.42
    균
    0.41
     /.
    0.41
    resonant
    0.41
    стями
    0.40
    Activations Density 0.003%

    No Known Activations