© 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. 101699
    Prev
    Next
    INDEX
    Explanations

    comment below

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

    marketing and 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
     [(
    0.51
     Mineral
    0.49
     qRT
    0.48
     immortal
    0.48
     हुये
    0.47
     mineral
    0.46
     pathophys
    0.46
     df
    0.46
     (%
    0.46
     Relating
    0.46
    POSITIVE LOGITS
    ুবাদ
    0.43
    ۲
    0.42
    ウォー
    0.41
    ძლი
    0.40
     ದಿ
    0.40
    दर्शिता
    0.40
    ၂
    0.39
    ೨
    0.39
     insistent
    0.39
    voicing
    0.39
    Activations Density 0.000%

    No Known Activations