© 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. 16-GEMMASCOPE-2-RES-262K
    4. 17636
    Prev
    Next
    INDEX
    Explanations

    Base64 encoded strings

    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_16_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
     is
    1.23
     of
    1.14
    ו
    1.11
     was
    0.99
     to
    0.97
     on
    0.95
    </h2>
    0.94
     by
    0.93
    	
    0.92
     in
    0.89
    POSITIVE LOGITS
    ⅾ
    0.91
    ન્મ
    0.89
     giugno
    0.86
     effectuées
    0.86
    iscono
    0.86
     informacije
    0.83
     potere
    0.82
    ید
    0.81
    aplic
    0.81
     effectué
    0.80
    Activations Density 0.001%

    No Known Activations