© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 120091
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specialized terms

    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
    ナン
    0.41
     imag
    0.39
     (%)
    0.38
     individually
    0.38
    ケーブル
    0.37
    個
    0.37
     PROTECTION
    0.36
    개를
    0.34
     cal
    0.34
     trái
    0.34
    POSITIVE LOGITS
     simonsen
    0.51
    क्टूबर
    0.46
     Flaxman
    0.45
    Iron
    0.44
    ፴
    0.42
     Iron
    0.42
    Ia
    0.41
     మైసూరు
    0.41
    ્ટ
    0.41
     hadronic
    0.41
    Activations Density 0.000%

    No Known Activations