© 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. 26753
    Prev
    Next
    INDEX
    Explanations

    "as is" phrase

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

    as is disclaimer

    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
    ამ
    0.50
    წ
    0.49
    槸
    0.46
    C
    0.45
    FromJson
    0.44
    ህ
    0.44
    優
    0.43
    whites
    0.42
    தேசம்
    0.42
    Y
    0.42
    POSITIVE LOGITS
     без
    0.54
     tanpa
    0.50
     الحال
    0.50
     unmodified
    0.48
     അവസ്ഥ
    0.47
    の状態
    0.47
     without
    0.47
     unchanged
    0.46
     pisc
    0.46
     unfiltered
    0.46
    Activations Density 0.000%

    No Known Activations