© 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. 245531
    Prev
    Next
    INDEX
    Explanations

    verbs and nouns before linking words

    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
    ប៉ុ
    0.46
    优
    0.45
     chính
    0.44
     s
    0.43
     وط
    0.42
     svou
    0.42
     ސ
    0.41
     ValueError
    0.41
    作为
    0.41
     případě
    0.40
    POSITIVE LOGITS
    '):
    0.52
     enacted
    0.52
    rahmen
    0.49
    )$:
    0.49
     loosened
    0.48
     paused
    0.45
    .):
    0.45
     verbunden
    0.44
     halved
    0.44
     transferable
    0.43
    Activations Density 0.001%

    No Known Activations