© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 89616
    Prev
    Next
    INDEX
    Explanations

    greeting traveler, bonus, entry, summoning, original, slip

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ien
    0.48
    För
    0.48
    Bir
    0.46
    ha
    0.46
    比
    0.46
    ää
    0.46
    /
    0.46
    0
    0.45
    ४
    0.45
    2
    0.45
    POSITIVE LOGITS
     wnios
    0.63
    كلات
    0.58
     Conclusions
    0.52
     Hooks
    0.52
     Defts
    0.51
    addAction
    0.50
     Actions
    0.49
     Schubert
    0.49
    ುವ
    0.49
     genealog
    0.48
    Activations Density 0.000%

    No Known Activations