© 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. 219696
    Prev
    Next
    INDEX
    Explanations

    verb + preposition or pronoun

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

    also include

    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
    रेक्ट
    0.47
     отсутствии
    0.47
    يا
    0.44
    ᔭ
    0.43
     acuerdo
    0.41
     Слова
    0.41
    ക്കുറ
    0.41
    ياً
    0.39
     Следу
    0.39
     illum
    0.39
    POSITIVE LOGITS
    ülmesi
    0.48
     mammals
    0.48
    繭
    0.45
     mitochond
    0.44
     millimeters
    0.43
    ారం
    0.41
     SDN
    0.41
    mamm
    0.41
     sigmoid
    0.40
     eukary
    0.40
    Activations Density 0.000%

    No Known Activations