© 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. 29926
    Prev
    Next
    INDEX
    Explanations

    vehicle movement, performance, infrastructure

    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
     rischio
    0.53
    ști
    0.48
     Сасик
    0.46
     மட்டும்
    0.44
     risked
    0.44
    mobilpay
    0.43
    Ｍ
    0.43
    ẓ
    0.43
    avacanam
    0.43
     격
    0.42
    POSITIVE LOGITS
    বর্ধ
    0.45
     s
    0.44
     separation
    0.43
     sådan
    0.43
     kalt
    0.41
     rates
    0.41
     troughs
    0.41
     degrees
    0.41
     brakes
    0.40
     ROAD
    0.40
    Activations Density 0.001%

    No Known Activations