© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 10435
    Prev
    Next
    INDEX
    Explanations

    specific phrases and conditions

    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
     l
    0.49
     and
    0.47
     
    0.47
     y
    0.42
     &
    0.42
     rectangular
    0.40
    9
    0.38
     Bal
    0.38
     four
    0.37
    4
    0.37
    POSITIVE LOGITS
    KeyboardView
    0.37
    зина
    0.36
     નજી
    0.36
    ાર
    0.36
    IsResolver
    0.35
    ROID
    0.35
    밖
    0.34
     других
    0.34
    UpperBound
    0.34
    রু
    0.34
    Activations Density 0.075%

    No Known Activations