© 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. 31584
    Prev
    Next
    INDEX
    Explanations

    Borin Stone beard

    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
    م
    1.27
    ۔
    1.10
    н
    1.08
    를
    1.07
    朋友
    1.06
    所有
    1.05
    ลม
    1.03
    는
    1.02
     on
    1.01
    м
    1.00
    POSITIVE LOGITS
    ين
    1.34
    id
    1.26
    ier
    1.22
    c
    1.21
    f
    1.19
    ков
    1.05
    af
    1.05
    ime
    1.04
    ie
    1.02
    oc
    1.01
    Activations Density 0.011%

    No Known Activations