© 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. 131358
    Prev
    Next
    INDEX
    Explanations

    WA Roofing Installer

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

    centering text and keywords

    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
    netje
    0.51
    ციის
    0.45
    мпаваць
    0.43
     devastating
    0.42
    çado
    0.42
    嗤
    0.41
    Manipulation
    0.41
    Gene
    0.41
    ترام
    0.41
     localisation
    0.40
    POSITIVE LOGITS
    i
    0.48
    '-
    0.45
     aynı
    0.45
     吸
    0.44
    LEC
    0.43
    APE
    0.42
                  
    0.42
    dialog
    0.42
     stron
    0.42
    ng
    0.42
    Activations Density 0.001%

    No Known Activations