© 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. 26893
    Prev
    Next
    INDEX
    Explanations

    bold text markers and content

    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
     انہیں
    0.48
     연결
    0.42
     تازہ
    0.41
    🩷
    0.40
     όλα
    0.40
     Цена
    0.40
    㧡
    0.40
    AllRef
    0.39
     створення
    0.39
    鈽
    0.39
    POSITIVE LOGITS
     permiss
    0.52
     susceptibility
    0.51
     prototypical
    0.50
     pathologies
    0.49
     empirically
    0.48
     inhibit
    0.47
     undermine
    0.47
     proliferation
    0.46
     tolerated
    0.46
     undermining
    0.46
    Activations Density 0.003%

    No Known Activations