© 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-65K
    7. 6987
    Prev
    Next
    INDEX
    Explanations

    offering options

    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_65k_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
    especially
    0.44
    adjust
    0.42
     ويك
    0.42
     લગભગ
    0.41
    ə
    0.39
    躏
    0.38
    add
    0.37
     männ
    0.36
    </li>
    0.36
    result
    0.36
    POSITIVE LOGITS
     either
    1.20
     entweder
    1.16
     Either
    1.16
    有两种
    1.13
    Either
    1.11
    两种
    1.09
    兩種
    1.08
    三种
    1.07
     options
    1.06
    几种
    1.04
    Activations Density 1.416%

    No Known Activations