© 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. 57944
    Prev
    Next
    INDEX
    Explanations

    multi-lingual content

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

    defining roles; specific clauses

    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
    IPO
    0.46
    кови
    0.46
    n
    0.46
    номет
    0.42
    上位
    0.42
    зыва
    0.41
    tender
    0.41
    随便
    0.40
    非常
    0.40
    shirts
    0.40
    POSITIVE LOGITS
    ۵
    0.60
     عملی
    0.51
     طریقے
    0.50
     आश्चर्य
    0.49
     यू
    0.48
     করিবে
    0.48
     توصیه
    0.48
     concentración
    0.48
     nematodes
    0.48
     bölümde
    0.47
    Activations Density 0.000%

    No Known Activations