© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 287
    Prev
    Next
    INDEX
    Explanations

    dialogue attribution for names

    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_16k_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
     %
    0.27
     ).
    0.23
     )
    0.22
     även
    0.20
     ஆகியவை
    0.20
     x
    0.20
     >
    0.20
     ),
    0.19
     ]
    0.19
     teie
    0.19
    POSITIVE LOGITS
    ando
    0.19
    nie
    0.18
    ceau
    0.18
    abeth
    0.18
    aza
    0.18
     himself
    0.17
    ian
    0.17
    aki
    0.17
     нау
    0.17
    andin
    0.17
    Activations Density 0.231%

    No Known Activations