© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 208258
    Prev
    Next
    INDEX
    Explanations

    following `you`

    np_acts-logits-general · gemini-2.5-flash-lite

    exploding gradients

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     \
    0.47
     lingered
    0.46
     wand
    0.44
     rights
    0.42
    jg
    0.42
     resided
    0.41
    ipp
    0.41
     seven
    0.40
     clarified
    0.40
    irio
    0.40
    POSITIVE LOGITS
    لسط
    0.47
    عند
    0.46
     التن
    0.44
    Automation
    0.44
     لحد
    0.43
    🧅
    0.43
    ؟
    0.43
    राबाद
    0.42
    Jetzt
    0.42
    ف
    0.42
    Activations Density 0.001%

    No Known Activations