© 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. 232744
    Prev
    Next
    INDEX
    Explanations

    guttering and downspouts

    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
    ‐
    0.46
    </tr>
    0.44
    }$(
    0.43
     downstream
    0.43
    які
    0.43
    </strong>
    0.42
                  
    0.42
    कर
    0.41
    зера
    0.41
                                   
    0.41
    POSITIVE LOGITS
    胿
    0.54
     القيام
    0.48
    ềm
    0.46
     세상
    0.46
    肚
    0.45
     publish
    0.44
    esinde
    0.44
     prettier
    0.44
     correctamente
    0.43
     మనం
    0.43
    Activations Density 0.001%

    No Known Activations