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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 131305
    Prev
    Next
    INDEX
    Explanations

    Billion Bottleneck, If Conditionals

    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
    GlobalSection
    0.45
    ್ಟ
    0.45
     алу
    0.41
    ջ
    0.40
    ృష్టి
    0.39
    がございます
    0.38
    rimidin
    0.38
    𒉡
    0.38
    
    0.37
    irond
    0.37
    POSITIVE LOGITS
     xanh
    0.37
     يكن
    0.36
    हुल
    0.36
     converts
    0.35
     शॉर्ट
    0.35
    Bots
    0.35
     дат
    0.35
     volte
    0.35
     whitening
    0.35
    Basketball
    0.35
    Activations Density 0.000%

    No Known Activations