© 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. 30777
    Prev
    Next
    INDEX
    Explanations

    qualified concrete nouns

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

    word followed by descriptor

    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
     abnormally
    0.44
     ہونا
    0.43
     매우
    0.43
    娆
    0.42
     уя
    0.41
     होना
    0.41
    ὥ
    0.40
     vertebrae
    0.40
     определение
    0.40
     aggravating
    0.39
    POSITIVE LOGITS
    -
    0.75
    による
    0.74
    based
    0.67
    Based
    0.60
    ভিত্তিক
    0.56
    ed
    0.54
     based
    0.53
    }$-
    0.48
    achtige
    0.48
     による
    0.48
    Activations Density 0.114%

    No Known Activations