© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 13053
    Prev
    Next
    INDEX
    Explanations

    google.dev links

    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
    سی
    0.55
     लो
    0.52
     teoría
    0.51
    می
    0.50
     traitement
    0.50
     teoria
    0.50
    گیری
    0.49
    ਤ
    0.49
    Ethiop
    0.48
     possibilit
    0.48
    POSITIVE LOGITS
     ఉంది
    0.48
    </code>
    0.42
     Pogis
    0.42
     announced
    0.41
    zę
    0.41
     Ihnen
    0.40
    ząc
    0.40
     Teams
    0.39
     القوه
    0.39
     Tape
    0.39
    Activations Density 0.083%

    No Known Activations