© 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. 98812
    Prev
    Next
    INDEX
    Explanations

    legal claims, data protection, circulating hot water

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

    but acknowledging difficulty

    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
     Tasty
    0.50
     Engineers
    0.47
     Weapons
    0.45
     Celebration
    0.45
     Rigid
    0.45
     payoffs
    0.44
     Davy
    0.44
    D
    0.44
     Brown
    0.44
     payload
    0.44
    POSITIVE LOGITS
    issense
    0.54
    allaitement
    0.51
    ᅪ
    0.50
    ită
    0.49
    sped
    0.49
    ekten
    0.49
    resposta
    0.49
    ❽
    0.48
    ibli
    0.48
    ță
    0.48
    Activations Density 0.001%

    No Known Activations