© 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. 179261
    Prev
    Next
    INDEX
    Explanations

    gift wrapping service

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

    often called, followed by specific nouns

    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
     quedado
    0.47
    の上
    0.45
    Andreas
    0.45
     intestino
    0.44
     jednym
    0.44
     hasilnya
    0.44
    䅡
    0.44
     одного
    0.43
     brauchen
    0.43
    Reviewed
    0.43
    POSITIVE LOGITS
    1
    0.54
    itter
    0.52
    lun
    0.52
    מצע
    0.51
    rid
    0.50
    lan
    0.50
     Valley
    0.49
    zim
    0.48
    mayan
    0.48
    loc
    0.48
    Activations Density 0.000%

    No Known Activations