© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9237
    Prev
    Next
    INDEX
    Explanations

    Temple of Heaven, Bridge of Sighs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_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
    usions
    1.24
    м
    1.15
    romantic
    1.12
     romantic
    1.10
    iteration
    1.09
    绚
    1.08
    relation
    1.08
    darkMode
    1.07
    iterations
    1.07
    mein
    1.05
    POSITIVE LOGITS
    大きい
    1.16
    いま
    1.09
     avis
    1.06
     esso
    1.05
     onderdeel
    1.04
     impede
    1.03
     importance
    1.01
     sitzt
    1.00
     も
    1.00
     happens
    0.99
    Activations Density 0.001%

    No Known Activations