© 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. 120911
    Prev
    Next
    INDEX
    Explanations

    additional features or services

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

    spell/trap cards

    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
    讣
    0.53
    翀
    0.50
     tất
    0.50
     semuanya
    0.49
    EEG
    0.49
    绉
    0.49
    卢
    0.48
     两
    0.48
    ண்ட்
    0.48
    Herkese
    0.48
    POSITIVE LOGITS
     useParams
    0.47
     explosives
    0.46
    시험
    0.44
    ctype
    0.43
     radioactivity
    0.42
    icrob
    0.42
     fever
    0.42
     রস
    0.41
    次の
    0.41
    sodium
    0.41
    Activations Density 0.000%

    No Known Activations