© 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. 120431
    Prev
    Next
    INDEX
    Explanations

    know, hemisphere, afternoon

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

    drawer contents

    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
    WRITE
    0.44
    INCLUDE
    0.43
     licenc
    0.43
    ﮈ
    0.43
    WIRE
    0.42
    勛
    0.42
     transferência
    0.42
    QU
    0.41
    JECT
    0.41
    WORTH
    0.41
    POSITIVE LOGITS
    oscopy
    0.48
    fels
    0.48
    amentos
    0.48
    ariums
    0.46
    amps
    0.46
    shore
    0.45
    ents
    0.45
    elä
    0.45
    abilität
    0.44
    髂
    0.44
    Activations Density 0.002%

    No Known Activations