© 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. 160965
    Prev
    Next
    INDEX
    Explanations

    sequences of common words

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

    why questions

    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
     outfitted
    0.48
     obeyed
    0.47
     mencionado
    0.47
    ற்றிய
    0.46
    engo
    0.46
    鳎
    0.46
     принял
    0.46
     aforesaid
    0.46
    朮
    0.45
     યોગ્ય
    0.44
    POSITIVE LOGITS
    貸
    0.48
     coexistence
    0.48
    civil
    0.46
     sprout
    0.46
     mollus
    0.46
    for
    0.45
    大
    0.44
     roll
    0.44
    scape
    0.44
    كي
    0.44
    Activations Density 0.001%

    No Known Activations