© 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. 31901
    Prev
    Next
    INDEX
    Explanations

    circuit diagram annotations

    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
    гра
    0.42
    Lion
    0.41
     paket
    0.39
     வரி
    0.38
     கொ
    0.37
    צו
    0.37
    رد
    0.36
    篙
    0.36
     பாக
    0.36
    ورية
    0.36
    POSITIVE LOGITS
     Rand
    0.38
     membre
    0.36
    దీ
    0.35
    ამის
    0.35
     члена
    0.35
     představ
    0.34
     Berechnung
    0.34
     protes
    0.34
     कंफ
    0.34
    eqnarray
    0.33
    Activations Density 0.000%

    No Known Activations