© 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. 31-GEMMASCOPE-2-RES-262K
    7. 57136
    Prev
    Next
    INDEX
    Explanations

    understand, tune, need, weave

    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_31_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
    យៈ
    0.44
     cartridges
    0.44
     unconsciously
    0.41
    로서
    0.41
     materi
    0.39
     dearest
    0.38
     careless
    0.38
    ዷ
    0.38
     cartridge
    0.37
    }=(-
    0.37
    POSITIVE LOGITS
    ających
    0.49
    ın
    0.47
    Planning
    0.46
     Planning
    0.46
     zaji
    0.45
    ungkan
    0.45
    skateboard
    0.44
    au
    0.43
     সরাসরি
    0.43
    gluten
    0.43
    Activations Density 0.003%

    No Known Activations