© 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. 40-GEMMASCOPE-2-RES-262K
    7. 22973
    Prev
    Next
    INDEX
    Explanations

    structured delimiters

    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_40_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
    敺
    0.45
    轺
    0.43
    conda
    0.42
    getCQL
    0.42
    赭
    0.42
    㞖
    0.41
    <unused57>
    0.41
    ୌ
    0.41
    膂
    0.41
     দ্বিত
    0.40
    POSITIVE LOGITS
    (_
    0.53
     _
    0.49
     (_
    0.46
    ("_
    0.45
    [_
    0.43
    =_
    0.42
    >(_
    0.41
     "_
    0.41
    _
    0.41
    }_
    0.40
    Activations Density 0.001%

    No Known Activations