© 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-65K
    7. 52138
    Prev
    Next
    INDEX
    Explanations

    structure definition

    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_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
     přip
    0.44
     الز
    0.43
     aż
    0.43
    וב
    0.42
    −</
    0.42
    鎸
    0.42
     totiž
    0.42
    ׃
    0.42
    слі
    0.41
    Bechyné
    0.41
    POSITIVE LOGITS
    \
    0.45
     travels
    0.44
     расположены
    0.40
    ↵
    0.40
                    
    0.39
    <unused2121>
    0.39
    ↵↵
    0.38
     ಔಷಧ
    0.38
    0.38
     closed
    0.38
    Activations Density 0.000%

    No Known Activations