© 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. 124326
    Prev
    Next
    INDEX
    Explanations

    last few letters of words

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

    et al

    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
    }
    0.52
    를
    0.51
    を
    0.49
    are
    0.49
    тов
    0.46
    /**
    0.45
    ou
    0.45
    에서
    0.43
     в
    0.43
     зав
    0.42
    POSITIVE LOGITS
     audioElement
    0.48
    distanceArray
    0.46
     meriye
    0.46
     ውሃ
    0.45
    ाइए
    0.43
     treści
    0.43
     buono
    0.42
     došlo
    0.42
    BtnFill
    0.42
     设备
    0.42
    Activations Density 0.002%

    No Known Activations