© 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. 12694
    Prev
    Next
    INDEX
    Explanations

    technical needs and personal admissions

    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
     পল্ল
    0.50
     precisión
    0.50
    碖
    0.49
     appliquer
    0.47
     unsustainable
    0.47
     aktivieren
    0.47
    સ
    0.47
    䚲
    0.47
    编辑器
    0.46
    َرْ
    0.45
    POSITIVE LOGITS
    an
    0.50
     vir
    0.45
    Trade
    0.44
    amines
    0.43
    late
    0.43
     Virtue
    0.43
    Charg
    0.43
    ado
    0.43
     no
    0.42
    ican
    0.42
    Activations Density 0.001%

    No Known Activations