Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 85480
    Prev
    Next
    INDEX
    Explanations

    non-english words

    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
    </b>
    0.45
    ;
    0.44
     размера
    0.42
     ponerse
    0.42
    й
    0.41
     необходимых
    0.40
    ites
    0.38
    чим
    0.38
    ).
    0.38
    </i>
    0.38
    POSITIVE LOGITS
    cartes
    0.49
     pièces
    0.46
     waarde
    0.46
     znač
    0.46
     frü
    0.45
    कता
    0.45
     trotz
    0.45
    ISI
    0.44
    තා
    0.44
    频
    0.44
    Activations Density 0.001%

    No Known Activations