© 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. 41-GEMMASCOPE-2-RES-262K
    7. 25287
    Prev
    Next
    INDEX
    Explanations

    track and trackable

    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_all/layer_41_width_262k_l0_big
    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
    э
    0.45
    <0x80>
    0.44
    ară
    0.44
    ี
    0.44
    ные
    0.44
    >
    0.44
    ী
    0.43
     результатом
    0.42
    佇
    0.42
    ті
    0.42
    POSITIVE LOGITS
    追踪
    0.60
     tracking
    0.58
    h
    0.58
    n
    0.55
    v
    0.55
    down
    0.53
    tracking
    0.53
    j
    0.53
     Track
    0.52
     Tracking
    0.52
    Activations Density 0.001%

    No Known Activations