Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 165439
    Prev
    Next
    INDEX
    Explanations

    ASCII art

    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_40_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
     قريب
    0.45
    čné
    0.45
     außer
    0.45
     نہيں
    0.45
    čené
    0.45
    })$-
    0.44
    szer
    0.44
     עד
    0.42
     ער
    0.42
     літоў
    0.42
    POSITIVE LOGITS
    I
    0.55
    board
    0.50
    iml
    0.49
    itm
    0.48
    alt
    0.47
     nook
    0.47
    findings
    0.47
    >>>
    0.47
     settling
    0.47
    inspect
    0.47
    Activations Density 0.014%

    No Known Activations