© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 3632
    Prev
    Next
    INDEX
    Explanations

    two or more

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    मुना
    0.26
     pouvoirs
    0.26
    役割
    0.26
    ینګ
    0.26
     rayons
    0.26
     másik
    0.26
    像
    0.26
     حيات
    0.26
    Reservation
    0.25
    Zespół
    0.25
    POSITIVE LOGITS
    adoc
    0.30
    uo
    0.30
    ‚
    0.28
    ol
    0.26
    itable
    0.26
    uar
    0.25
    oa
    0.25
    ă
    0.25
    u
    0.25
     stated
    0.25
    Activations Density 0.884%

    No Known Activations