© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 32902
    Prev
    Next
    INDEX
    Explanations

    breaking America, to achieve, by threatening

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

    private sale

    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
     abomin
    0.48
     nette
    0.45
    ]",
    0.45
    fonos
    0.44
    spaper
    0.44
    ]
    0.43
     FI
    0.43
     produces
    0.42
     segno
    0.42
     た
    0.41
    POSITIVE LOGITS
     ఆట
    0.50
    𝐠
    0.49
    狀況
    0.49
     reallocation
    0.49
     sửa
    0.48
    髹
    0.47
     giấc
    0.46
     plabic
    0.46
     알아
    0.46
    거
    0.46
    Activations Density 0.000%

    No Known Activations