© 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. 3232
    Prev
    Next
    INDEX
    Explanations

    verbs in sentences

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

    grammar and sentence agreement

    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
    恶意
    0.41
     débit
    0.40
     защиту
    0.39
     protezione
    0.39
    GOR
    0.39
    啖
    0.38
     zabezpie
    0.38
    filer
    0.38
    duk
    0.38
    >');
    0.37
    POSITIVE LOGITS
     sentences
    0.49
     Present
    0.48
     Singular
    0.48
     subjunctive
    0.47
    singular
    0.45
     Veget
    0.44
     Sources
    0.44
     cümle
    0.43
     Sentence
    0.43
     presentes
    0.42
    Activations Density 0.006%

    No Known Activations