© 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. 100467
    Prev
    Next
    INDEX
    Explanations

    planning activities and events

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

    scheduled events, colloquial phrases

    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
    )
    0.56
    }
    0.52
     colorful
    0.46
    ulares
    0.45
    ']
    0.45
     playful
    0.45
     candied
    0.45
     variety
    0.44
    ')
    0.44
    Inicial
    0.44
    POSITIVE LOGITS
    στή
    0.53
     খাতে
    0.49
    चिंत
    0.48
    
    0.46
    perceptron
    0.45
    锻炼
    0.45
     huidige
    0.44
     সংগ্রামী
    0.44
    hydroxy
    0.44
    सी
    0.44
    Activations Density 0.001%

    No Known Activations