© 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. 31-GEMMASCOPE-2-RES-262K
    7. 43592
    Prev
    Next
    INDEX
    Explanations

    explosive compounds, phase relationships, collaborative annotation

    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
     unavoid
    0.49
     currentGame
    0.45
    េង
    0.44
     deshalb
    0.43
    Chhattisgarh
    0.42
     $(".
    0.42
     dáv
    0.42
     unchecked
    0.42
     Manipur
    0.42
     $('.
    0.41
    POSITIVE LOGITS
     Flies
    0.48
    lt
    0.44
    杀
    0.43
    etics
    0.42
    의
    0.42
    ters
    0.42
    uses
    0.41
    enses
    0.40
    mer
    0.40
    led
    0.40
    Activations Density 0.001%

    No Known Activations