© 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. 151574
    Prev
    Next
    INDEX
    Explanations

    growth rate

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

    dichromatic vision

    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
    Ҷ
    0.56
     nowych
    0.52
     spettac
    0.52
    Chicken
    0.51
    Melbourne
    0.51
    ல்களில்
    0.51
    Bundes
    0.50
     journaliste
    0.50
    Farm
    0.50
    Chelsea
    0.50
    POSITIVE LOGITS
    adr
    0.54
    ”
    0.50
     తెలి
    0.46
    öd
    0.46
    mus
    0.45
     बर
    0.45
     healing
    0.45
    avali
    0.45
    ],”
    0.43
    zas
    0.42
    Activations Density 0.003%

    No Known Activations