© 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. 79704
    Prev
    Next
    INDEX
    Explanations

    study guides and course Catalogs

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

    technical requirements

    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
    roleum
    0.44
     Flora
    0.40
    П
    0.39
    studio
    0.38
    levelup
    0.38
    ers
    0.38
    edos
    0.37
    스
    0.36
    urally
    0.36
     Diana
    0.36
    POSITIVE LOGITS
     religión
    0.52
     inode
    0.44
    )),
    0.42
     decret
    0.42
     concili
    0.42
    )=
    0.40
    )`,
    0.40
     forc
    0.40
     గవర్
    0.40
    ਾਰ
    0.40
    Activations Density 0.000%

    No Known Activations