© 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. 227632
    Prev
    Next
    INDEX
    Explanations

    periods

    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
     لکھ
    0.48
     organismo
    0.48
    mixture
    0.44
    プレイ
    0.44
    grow
    0.43
     insufficiently
    0.43
     μά
    0.42
    蒼
    0.42
    hernalia
    0.42
     plasmids
    0.41
    POSITIVE LOGITS
     RFID
    0.48
     CLEAN
    0.47
    㕲
    0.45
    elink
    0.45
    ard
    0.45
    ata
    0.45
     CRIS
    0.44
    popsicle
    0.44
     reimag
    0.44
    orative
    0.44
    Activations Density 0.003%

    No Known Activations