© 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. 121105
    Prev
    Next
    INDEX
    Explanations

    miss classes

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

    brains are wired/learn

    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
    முத
    0.38
     ※
    0.38
     shoots
    0.38
     mouse
    0.36
     Played
    0.36
     respectivamente
    0.36
     क्रमशः
    0.36
     njegov
    0.35
     Awak
    0.35
     inicialmente
    0.35
    POSITIVE LOGITS
    ningar
    0.51
    Ṣ
    0.48
     場
    0.47
    楨
    0.47
     কিনতে
    0.46
     എന്നത്
    0.46
    ที่จะ
    0.46
     Ghar
    0.45
     ର
    0.45
    磧
    0.45
    Activations Density 0.001%

    No Known Activations