© 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. 173294
    Prev
    Next
    INDEX
    Explanations

    years, win, zero

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

    simple shapes, black hair, achieving neutrality

    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
    Ethyl
    0.46
    莠
    0.46
    玹
    0.44
    })$,
    0.43
    匏
    0.43
    ще
    0.43
    부분
    0.42
    गिर
    0.42
    畯
    0.41
    драт
    0.41
    POSITIVE LOGITS
     caching
    0.50
    fetched
    0.46
     synovial
    0.46
     having
    0.46
     lymphatic
    0.46
     fetching
    0.45
     retrieving
    0.45
     bushy
    0.45
     achieving
    0.45
     बीते
    0.45
    Activations Density 0.001%

    No Known Activations