© 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. 29-GEMMASCOPE-2-RES-262K
    7. 148977
    Prev
    Next
    INDEX
    Explanations

    broken, stained, shattered glass

    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_29_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
     nodes
    0.80
     PUL
    0.76
    NODE
    0.75
     node
    0.75
     Rhythm
    0.74
    putnik
    0.74
     Sputnik
    0.71
    樋
    0.71
     Rotor
    0.68
     rotor
    0.68
    POSITIVE LOGITS
     glass
    2.91
     Glass
    2.73
    Glass
    2.66
    glass
    2.60
     GLASS
    2.45
    玻璃
    2.34
    GLASS
    2.24
     glasses
    2.22
    ガラス
    2.20
     Glas
    2.15
    Activations Density 0.016%

    No Known Activations