© 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. 223041
    Prev
    Next
    INDEX
    Explanations

    acre parcel

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

    wiped down

    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
    項
    0.50
    目の
    0.50
    다면
    0.48
    ণ
    0.47
    傭
    0.46
     lymph
    0.45
    ง่าย
    0.45
    ك
    0.45
    어
    0.45
     the
    0.45
    POSITIVE LOGITS
     carinatis
    0.57
    strates
    0.52
     później
    0.50
     വിജ
    0.48
    }}:=\
    0.48
    closes
    0.48
    obod
    0.48
     avem
    0.47
     kült
    0.47
    }}}+\
    0.47
    Activations Density 0.000%

    No Known Activations