© 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. 156353
    Prev
    Next
    INDEX
    Explanations

    transit hubs, venue negotiations, pinned down, obtained from

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

    wedding invitation

    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
    </h2>
    0.49
    Ending
    0.49
     Does
    0.47
     Расійскай
    0.46
    ที่จะ
    0.45
    muscle
    0.44
    =="
    0.44
    Challenges
    0.44
    andha
    0.43
    atina
    0.43
    POSITIVE LOGITS
    }^{-},
    0.49
     cé
    0.49
     appliqué
    0.48
    エム
    0.48
    ብሰ
    0.48
    內
    0.46
    葢
    0.46
     ],
    0.46
    ný
    0.46
    용한
    0.45
    Activations Density 0.001%

    No Known Activations