© 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. 173175
    Prev
    Next
    INDEX
    Explanations

    accessories of the Magnetika collection

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

    police brutality against, common subsequences, primordial fire, Expat Appeal

    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
     प्रत्येक
    0.46
     each
    0.45
    ના
    0.45
    emoji
    0.44
     Each
    0.44
    🤬
    0.42
    Bootstrap
    0.42
    काच्या
    0.42
    gete
    0.41
     डैम
    0.41
    POSITIVE LOGITS
     légion
    0.51
     legion
    0.50
     contento
    0.49
     ဝ
    0.48
     Legion
    0.47
     constellation
    0.47
     résident
    0.46
     iniziare
    0.45
    ্যান্ড
    0.44
     gearing
    0.44
    Activations Density 0.001%

    No Known Activations