© 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. 131873
    Prev
    Next
    INDEX
    Explanations

    technical terms or concepts

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

    `public building`, `arable land`, `focused approach`

    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
    。
    0.57
    }$.
    0.51
    Об
    0.47
    ։
    0.47
    。\
    0.46
    ।
    0.46
    }(\
    0.46
    ™.
    0.45
    最適
    0.45
    ۔
    0.45
    POSITIVE LOGITS
     ambulances
    0.43
     drugs
    0.39
     opioids
    0.37
     যতই
    0.36
    padx
    0.36
     pharmaceuticals
    0.36
     پڑے
    0.36
     medicines
    0.35
     pavement
    0.35
     exerts
    0.35
    Activations Density 0.066%

    No Known Activations