© 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. 131428
    Prev
    Next
    INDEX
    Explanations

    without preceding or following phrases

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

    lack of knowledge or access

    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
     methylene
    0.51
     henna
    0.45
     όταν
    0.45
     penggunaan
    0.43
    当我们
    0.43
    亞
    0.43
     when
    0.42
    িরের
    0.42
     ferritin
    0.42
    ।
    0.42
    POSITIVE LOGITS
     wretched
    0.53
     മുഴുവ
    0.50
    ème
    0.47
     profondes
    0.46
     relentlessly
    0.46
     Freude
    0.45
     Untold
    0.44
    ích
    0.43
     समृ
    0.43
     असंख्य
    0.43
    Activations Density 0.065%

    No Known Activations