© 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. 128537
    Prev
    Next
    INDEX
    Explanations

    names, equal, recorded, barrier

    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
     labios
    0.50
    0
    0.50
    W
    0.47
    OC
    0.47
    atorio
    0.47
    7
    0.46
    ANTS
    0.46
    5
    0.45
    AX
    0.45
    ATIC
    0.45
    POSITIVE LOGITS
    ਫ਼
    0.45
     pandémie
    0.43
    టమి
    0.42
    舉辦
    0.42
    ూరు
    0.42
    艱
    0.41
    ጠና
    0.41
     році
    0.41
    모델
    0.41
     собы
    0.40
    Activations Density 0.004%

    No Known Activations