© 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. 80320
    Prev
    Next
    INDEX
    Explanations

    array of objects

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

    Early and historical events

    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
    بال
    0.64
    צור
    0.63
     devam
    0.59
    ור
    0.57
    쥬
    0.55
    暠
    0.54
    обо
    0.54
    뛴
    0.52
    螈
    0.51
    არა
    0.51
    POSITIVE LOGITS
     facilitators
    0.45
     PAT
    0.44
     advertisers
    0.43
     prohibitions
    0.43
     aerosol
    0.42
     acquis
    0.42
     bottled
    0.42
     discretion
    0.42
     aerosols
    0.42
     seventies
    0.42
    Activations Density 0.000%

    No Known Activations