© 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. 16-GEMMASCOPE-2-RES-65K
    7. 2892
    Prev
    Next
    INDEX
    Explanations

    code with `self`

    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_16_width_65k_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
    E
    1.70
    I
    1.61
    O
    1.34
    AN
    1.33
    L
    1.32
    EP
    1.24
    ED
    1.21
    H
    1.20
    EST
    1.17
    EZ
    1.17
    POSITIVE LOGITS
    л
    1.18
    ção
    0.99
    の
    0.99
    스는
    0.98
    zelfde
    0.94
    ки
    0.91
    ]
    0.91
    लिये
    0.90
    ı
    0.87
    կ
    0.87
    Activations Density 0.287%

    No Known Activations