© 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. 246199
    Prev
    Next
    INDEX
    Explanations

    choosing or includes

    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
    isać
    0.63
    பா
    0.54
    ہ
    0.53
     acabou
    0.52
    lanır
    0.51
    ები
    0.51
     کرے
    0.49
    aság
    0.49
    ፩
    0.49
     aspetti
    0.48
    POSITIVE LOGITS
    s
    0.58
    EM
    0.51
     S
    0.49
     Science
    0.48
     LED
    0.47
     log
    0.47
     EM
    0.46
    7
    0.45
    all
    0.45
    Science
    0.44
    Activations Density 0.000%

    No Known Activations