© 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. 206933
    Prev
    Next
    INDEX
    Explanations

    updates information, drivers

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

    business structuring options

    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
    কথা
    0.45
    꽂
    0.41
     plötzlich
    0.40
    াধ্য
    0.40
    Callories
    0.38
     अभिव्य
    0.38
     transcriptional
    0.37
    chio
    0.37
    চিতের
    0.37
    parseLong
    0.37
    POSITIVE LOGITS
     необходимые
    0.51
     necesario
    0.50
    ซี
    0.48
     जाएगी
    0.46
     खतर
    0.46
     городской
    0.45
    ۳
    0.45
     کل
    0.44
    ließt
    0.44
     niezbęd
    0.44
    Activations Density 0.001%

    No Known Activations