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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 43355
    Prev
    Next
    INDEX
    Explanations

    using calculations

    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
    σα
    0.50
    ಾಯಕ
    0.49
    ghar
    0.46
    !")
    0.45
     Piy
    0.44
     ର
    0.43
    寘
    0.43
    র্ণ
    0.43
    ?")
    0.43
    unghi
    0.43
    POSITIVE LOGITS
     दोन
    0.45
    幼稚園
    0.44
    উঠ
    0.44
    </h3>
    0.42
    ത്തോടെ
    0.42
     புரிந்து
    0.41
    പ്പാ
    0.41
    .);
    0.41
     telefoon
    0.40
    </h4>
    0.40
    Activations Density 0.004%

    No Known Activations