© 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. 13554
    Prev
    Next
    INDEX
    Explanations

    phrases with numbers or special characters

    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
     мебели
    0.10
     хотела
    0.10
    鉈
    0.10
     ລັບ
    0.10
     తగ్
    0.09
     vasomotor
    0.09
    ويس
    0.09
     мебель
    0.09
     مذہ
    0.09
     проводится
    0.09
    POSITIVE LOGITS
     UnityEngine
    0.10
    为
    0.10
    ن
    0.09
     Spine
    0.09
     Deep
    0.09
    일
    0.09
    var
    0.09
     Dummy
    0.09
    name
    0.09
     Alpha
    0.09
    Activations Density 0.006%

    No Known Activations