© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 79903
    Prev
    Next
    INDEX
    Explanations

    airport and security phrases

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

    it excels, lacks general intelligence

    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
    н
    0.48
    Uns
    0.46
    кир
    0.46
    Ľ
    0.46
    ignored
    0.45
    Echo
    0.45
    σ
    0.44
    IVER
    0.44
    leva
    0.43
    醫
    0.43
    POSITIVE LOGITS
     WHERE
    0.50
     高さ
    0.46
     varies
    0.45
     ہے۔
    0.44
     chamb
    0.43
     especies
    0.43
     occupé
    0.43
    اہے
    0.43
    তনে
    0.42
     ঘনত্ব
    0.42
    Activations Density 0.000%

    No Known Activations