© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 32162
    Prev
    Next
    INDEX
    Explanations

    preposition and determiner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.43
     swelling
    0.43
    絶
    0.42
     or
    0.38
     That
    0.38
     stif
    0.37
     Digests
    0.37
     Damen
    0.37
     bolstering
    0.37
     '
    0.36
    POSITIVE LOGITS
    ﺏ
    0.49
     yapacağız
    0.48
     इजी
    0.47
    iliśmy
    0.47
    र्नल
    0.47
    Aprend
    0.47
    फोर
    0.46
    अमेर
    0.46
    蟋
    0.46
    ट्रा
    0.45
    Activations Density 0.000%

    No Known Activations