© 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-16K
    7. 12544
    Prev
    Next
    INDEX
    Explanations

    functionality and operational status

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

    explaining how it works

    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_16k_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
    ᄈ
    0.47
    cloud
    0.46
    iul
    0.44
    Cloud
    0.43
    Emmanuel
    0.43
     सड़कें
    0.42
    OTT
    0.42
    붕
    0.42
    Sandra
    0.41
    Yu
    0.41
    POSITIVE LOGITS
     dynamique
    0.46
     üld
    0.44
     blames
    0.44
    জিওথেরাপি
    0.43
     allegations
    0.43
     Itali
    0.42
     worthwhile
    0.42
     pelaksanaan
    0.41
     operative
    0.41
     dilaksanakan
    0.41
    Activations Density 0.000%

    No Known Activations