© 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-16K
    7. 12766
    Prev
    Next
    INDEX
    Explanations

    international pioneer, small roles, user usage, writing operation, cities circuit, access restriction

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

    non-english words and academic concepts

    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_16k_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
    птова
    0.42
     mathrm
    0.41
     bestselling
    0.40
     σε
    0.39
     your
    0.39
    র্জাতিক
    0.39
     {@
    0.39
    のに
    0.38
     \
    0.37
    templatemo
    0.37
    POSITIVE LOGITS
    నం
    0.38
     ведь
    0.38
    existent
    0.36
     அவர்களை
    0.36
    வம்
    0.35
     அவர்களிடம்
    0.34
    钢铁
    0.34
    ্ড
    0.34
     אות
    0.33
    imit
    0.33
    Activations Density 0.015%

    No Known Activations