© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 193895
    Prev
    Next
    INDEX
    Explanations

    code context

    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
     an
    0.44
    剥
    0.42
     electron
    0.39
     Crick
    0.38
    Increment
    0.38
     निर्दिष्ट
    0.38
     Ax
    0.37
    Reduction
    0.37
    An
    0.36
    SELF
    0.36
    POSITIVE LOGITS
    pwm
    0.47
     clás
    0.39
     pwm
    0.38
    হত
    0.37
    werks
    0.37
    ુ
    0.37
    තා
    0.37
     grabado
    0.35
     Gerät
    0.35
     موج
    0.34
    Activations Density 0.000%

    No Known Activations