© 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. 218736
    Prev
    Next
    INDEX
    Explanations

    site visitors

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

    overlap

    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
    0.63
    ssr
    0.53
    9
    0.49
    ེ
    0.48
     Paste
    0.47
     Bus
    0.46
     Headlines
    0.46
    tv
    0.46
     $("#
    0.44
     You
    0.44
    POSITIVE LOGITS
     métallique
    0.47
     dismantled
    0.47
     руха
    0.47
     renom
    0.46
    க்கப்பட்ட
    0.46
     roya
    0.46
    ۟
    0.46
    ája
    0.44
     دلچ
    0.44
     جوړونک
    0.44
    Activations Density 0.000%

    No Known Activations