© 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. 218850
    Prev
    Next
    INDEX
    Explanations

    breathtaking, damaged, largest, container, leaders

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

    assessment and shaping language

    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
     ≥
    0.52
     वास्तविकता
    0.52
     Hotels
    0.52
     RECE
    0.52
     ROYAL
    0.51
     EXISTING
    0.51
     velič
    0.50
     애니
    0.50
     호텔
    0.50
    ⤠
    0.50
    POSITIVE LOGITS
     municipio
    0.48
    covered
    0.46
    نگ
    0.45
    مرة
    0.45
     mismatched
    0.45
    migrate
    0.44
    ছি
    0.44
    nicheskij
    0.44
    灘
    0.44
    ходил
    0.44
    Activations Density 0.001%

    No Known Activations