© 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. 90184
    Prev
    Next
    INDEX
    Explanations

    ceasefire, levels, harness, attorney, Layers

    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
    GoogleApiClient
    0.46
    ㅔ
    0.44
    <0x80>
    0.44
    itioner
    0.43
    vala
    0.43
    Dag
    0.43
    azard
    0.42
    랑
    0.42
    ับ
    0.42
    opro
    0.42
    POSITIVE LOGITS
     conflictos
    0.54
     intenz
    0.54
     ruptura
    0.52
     ત
    0.50
    𝙞
    0.50
     anticip
    0.49
     inteligencia
    0.49
     حتى
    0.47
     anz
    0.47
     encuentre
    0.47
    Activations Density 0.003%

    No Known Activations