© 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. 184906
    Prev
    Next
    INDEX
    Explanations

    international corporations, but we, end of, classes on

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

    LSM-trees, VBD, VDGs

    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
     schützen
    0.54
    }$
    0.46
     bato
    0.46
    }<
    0.45
    ’”
    0.45
     krijgen
    0.45
     Dov
    0.45
    Si
    0.45
    lois
    0.44
    }$\
    0.44
    POSITIVE LOGITS
    ά
    0.46
    iy
    0.45
    τε
    0.45
    کان
    0.45
    ীয়
    0.44
     càng
    0.44
     তথা
    0.43
    WallArray
    0.43
     یہودیوں
    0.43
     편리
    0.42
    Activations Density 0.001%

    No Known Activations