© 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. 88294
    Prev
    Next
    INDEX
    Explanations

    you outpart ofthe emergency% shareholdermultiplying ofto expressdirt willmany hadbut ,clues from

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

    linking to another file or inode

    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
    ه
    0.58
    ین
    0.51
    ی
    0.51
     berwarna
    0.47
     acompanhar
    0.46
     که
    0.44
    рода
    0.44
     হানি
    0.44
    انية
    0.43
    ردو
    0.43
    POSITIVE LOGITS
     c
    0.47
    温馨
    0.45
     admission
    0.43
    ıyordu
    0.43
    ovaniyu
    0.43
     pitchers
    0.43
    blos
    0.42
     Soho
    0.41
    Vault
    0.41
     Krä
    0.41
    Activations Density 0.001%

    No Known Activations