© 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. 40394
    Prev
    Next
    INDEX
    Explanations

    instructional verbs

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

    following state or object

    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
     шла
    0.44
    ┛
    0.44
    ﹍
    0.44
    蒺
    0.43
    ಬ್ಬಿಣ
    0.42
     burners
    0.39
     apron
    0.39
    /////////
    0.39
    bmp
    0.38
    mathop
    0.38
    POSITIVE LOGITS
     natürliche
    0.50
    再來
    0.45
     deus
    0.42
     Schreiben
    0.41
    ffi
    0.40
     tabii
    0.40
    ធម្ម
    0.40
     Ressourcen
    0.40
     Philosophie
    0.40
     després
    0.40
    Activations Density 0.001%

    No Known Activations