© 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. 22509
    Prev
    Next
    INDEX
    Explanations

    your items, high-quality, a receiving

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

    technical terms and concepts

    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
    tls
    0.44
    riva
    0.43
    開幕
    0.43
     শ্রীমতি
    0.42
    inesi
    0.41
    IY
    0.41
    勃
    0.41
    !\
    0.41
    ⛱
    0.41
    為
    0.40
    POSITIVE LOGITS
     förm
    0.45
     nettement
    0.44
     Muj
    0.43
    IndexOf
    0.43
     guère
    0.43
     rarement
    0.43
     chiar
    0.43
     dwóch
    0.43
     podía
    0.42
     کھیلنے
    0.41
    Activations Density 0.000%

    No Known Activations