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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169321
    Prev
    Next
    INDEX
    Explanations

    food items, outlines, wireframes, or titles

    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
    или
    0.50
     Сол
    0.49
    னால
    0.48
    Bats
    0.48
    ро
    0.44
     ато
    0.44
    ⴹ
    0.43
    혼
    0.43
     плане
    0.42
    цију
    0.42
    POSITIVE LOGITS
    }`
    0.50
    "."
    0.48
    လျ
    0.46
     pieno
    0.46
    }"
    0.45
    ],
    0.45
     IGD
    0.44
     Bhand
    0.43
     Ministers
    0.43
     Occupational
    0.43
    Activations Density 0.004%

    No Known Activations