© 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. 127747
    Prev
    Next
    INDEX
    Explanations

    liminality and transition

    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
     Bird
    0.55
     t
    0.51
    wil
    0.50
     Wil
    0.49
     Flower
    0.49
     for
    0.48
    }}
    0.48
     Nov
    0.48
     by
    0.47
     Maintenance
    0.47
    POSITIVE LOGITS
    ेलर
    0.52
     घेतले
    0.52
     thermodynam
    0.50
     noyau
    0.49
     만드는
    0.48
     忄
    0.47
    ANGMAR
    0.46
     içi
    0.46
     suffoc
    0.46
     만들
    0.46
    Activations Density 0.000%

    No Known Activations