© 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. 77605
    Prev
    Next
    INDEX
    Explanations

    relativity and anyone can

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

    structuring content or information

    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
    b
    0.62
    ᱫ
    0.47
    G
    0.47
     CEN
    0.47
    Sett
    0.47
    ТС
    0.45
     estan
    0.45
     consolid
    0.44
    Bs
    0.44
     পুরনো
    0.44
    POSITIVE LOGITS
    orrhea
    0.57
    arne
    0.49
    媺
    0.48
    itva
    0.45
    ിലൂടെ
    0.44
    셔서
    0.43
    แยก
    0.43
    ambahkan
    0.43
    <unused88>
    0.43
     Phuket
    0.43
    Activations Density 0.001%

    No Known Activations