© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 8878
    Prev
    Next
    INDEX
    Explanations

    dozen of

    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_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
     in
    1.28
    the
    1.09
    ;
    1.06
     In
    1.05
    ton
    1.05
    ]
    1.02
    ),
    0.98
     The
    0.97
    )
    0.96
    0
    0.96
    POSITIVE LOGITS
     powied
    1.21
    ين
    1.20
    வன்
    1.16
     сообщи
    1.15
    ра
    1.13
    ম
    1.12
    يف
    1.10
    な
    1.09
    ס
    1.09
    يد
    1.06
    Activations Density 0.006%

    No Known Activations