© 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. 243009
    Prev
    Next
    INDEX
    Explanations

    time and extent

    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
    ેચ્છ
    0.50
     হইতেই
    0.49
     flavonoids
    0.47
     TouchUtils
    0.46
    تيجة
    0.46
    ()].
    0.45
    ла
    0.45
    同樣
    0.44
     উত্তেজনা
    0.44
    駋
    0.44
    POSITIVE LOGITS
     parler
    0.46
     buss
    0.44
     घाल
    0.44
    ُم
    0.43
    様々な
    0.43
     വിവിധ
    0.43
     END
    0.42
    accompanied
    0.42
     subordination
    0.42
     przy
    0.41
    Activations Density 0.000%

    No Known Activations