© 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. 210942
    Prev
    Next
    INDEX
    Explanations

    observations and outcomes

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

    existing lenses

    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
     than
    0.58
     sustainable
    0.55
     dispositivi
    0.55
     ,
    0.53
     |
    0.53
     punto
    0.53
     sua
    0.52
     WLAN
    0.51
     sempre
    0.51
     strumenti
    0.51
    POSITIVE LOGITS
    Ꮆ
    0.47
    不满
    0.46
    حبه
    0.45
     заинтере
    0.45
    ána
    0.44
    getJSON
    0.44
    鎏
    0.44
    ક્
    0.44
    阏
    0.44
     исте
    0.43
    Activations Density 0.001%

    No Known Activations