© 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. 17629
    Prev
    Next
    INDEX
    Explanations

    24/7 support or hours

    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
    and
    1.00
    \
    0.94
    os
    0.93
    1
    0.88
    (
    0.84
    0
    0.84
    Fashion
    0.82
    ksiyon
    0.79
    Cantidad
    0.79
    enary
    0.78
    POSITIVE LOGITS
     to
    1.23
    д
    1.12
     can
    1.07
    ג
    1.07
    ه
    1.06
    र
    1.04
    г
    1.04
    دو
    0.96
    دى
    0.96
    يل
    0.95
    Activations Density 0.016%

    No Known Activations