© 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. 25740
    Prev
    Next
    INDEX
    Explanations

    following prepositions or specifications

    np_acts-logits-general · gemini-2.5-flash-lite

    exploration and discovery

    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
    ادرة
    0.50
    _
    0.47
    撾
    0.46
    রিষ্ঠ
    0.45
    詳
    0.45
    উর
    0.44
    uka
    0.44
    师
    0.43
    鱼
    0.43
    吵
    0.42
    POSITIVE LOGITS
    ObjectTemp
    0.53
    leven
    0.52
     вслед
    0.49
     จัก
    0.46
     점점
    0.46
    ானது
    0.46
     atteints
    0.46
     anteriormente
    0.45
    sequent
    0.45
     }+
    0.44
    Activations Density 0.000%

    No Known Activations