© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33823
    Prev
    Next
    INDEX
    Explanations

    street address parts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    {(-
    0.44
     kategor
    0.43
    ناه
    0.43
    露
    0.42
     baryon
    0.39
     genética
    0.38
    ிலிருந்து
    0.38
     Interessen
    0.38
     gorg
    0.38
     neutrinos
    0.38
    POSITIVE LOGITS
     street
    1.15
    street
    1.04
     Street
    1.01
    Street
    1.01
     streets
    0.88
     STREET
    0.88
    streets
    0.85
     Streets
    0.84
    街
    0.80
     स्ट्रीट
    0.79
    Activations Density 0.010%

    No Known Activations