© 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. 20268
    Prev
    Next
    INDEX
    Explanations

    items listed with descriptive words

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

    plural nouns followed by verbs/prepositions

    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
    The
    0.60
    in
    0.57
    Y
    0.56
         
    0.55
                    
    0.54
     The
    0.54
    E
    0.54
    一
    0.54
    ad
    0.53
    ž
    0.52
    POSITIVE LOGITS
     own
    0.61
     todays
    0.58
     newfound
    0.57
    몫
    0.56
    CEPTION
    0.54
     allegiance
    0.54
     میتوان
    0.54
     finest
    0.54
     propias
    0.54
     cualidades
    0.53
    Activations Density 0.085%

    No Known Activations