© 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. 70519
    Prev
    Next
    INDEX
    Explanations

    legal, financial, or professional terms

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

    causing problems

    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
     zelf
    0.48
    ebb
    0.45
    鎮
    0.44
    HF
    0.43
     تلك
    0.42
    deel
    0.42
     تلاميذ
    0.42
    VOL
    0.41
    роў
    0.40
     بناء
    0.39
    POSITIVE LOGITS
    眹
    0.48
     copyrights
    0.46
     assurances
    0.45
    ayati
    0.45
     आम्हाला
    0.45
     glories
    0.44
     মানবতার
    0.44
     피해
    0.44
     memoirs
    0.43
     आप
    0.43
    Activations Density 0.000%

    No Known Activations