© 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. 40-GEMMASCOPE-2-RES-262K
    7. 110682
    Prev
    Next
    INDEX
    Explanations

    bytes, int, hex, bytearray

    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
    binary
    0.38
    diamond
    0.38
    }_{-
    0.38
     backup
    0.37
     backups
    0.37
    financed
    0.37
     Funds
    0.36
    spir
    0.36
     निधी
    0.35
    goo
    0.35
    POSITIVE LOGITS
     কলেজের
    0.39
    ুকে
    0.38
     colleges
    0.38
    ಮಾ
    0.38
     atvej
    0.38
    ፴
    0.38
     লোককে
    0.38
     bevel
    0.37
     कॉलेज
    0.37
    ableConcept
    0.37
    Activations Density 0.004%

    No Known Activations