© 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. 177402
    Prev
    Next
    INDEX
    Explanations

    common noun phrases

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

    balanced growth, melancholy, film, Italy, gay, permanent residents

    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
    ujesz
    0.50
     giocatori
    0.49
    ikiem
    0.48
     choreographed
    0.46
     musician
    0.46
     ዳ
    0.45
    akiem
    0.45
     dalle
    0.44
     curated
    0.44
    getInfo
    0.44
    POSITIVE LOGITS
    كب
    0.42
    },
    0.42
    }.
    0.41
    一半
    0.39
    أ
    0.39
    ็ว
    0.39
    絨
    0.39
    ك
    0.38
     ص
    0.38
     periódico
    0.38
    Activations Density 0.000%

    No Known Activations