© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 193476
    Prev
    Next
    INDEX
    Explanations

    geographical terms and related concepts

    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_40_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
     अराउंड
    0.41
    elabor
    0.39
     평가
    0.38
     indígenas
    0.38
    欽
    0.38
     following
    0.37
    評価
    0.37
    メイク
    0.36
     ис
    0.36
     червня
    0.36
    POSITIVE LOGITS
     Tranqu
    0.38
     tranquility
    0.34
    箭
    0.34
     amus
    0.34
     detached
    0.34
    indelijk
    0.34
     disconnecting
    0.33
    实例
    0.33
     नेहमी
    0.32
    Ain
    0.32
    Activations Density 0.000%

    No Known Activations