© 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. 91772
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and 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_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
    ർഡ്
    0.53
    ermat
    0.50
     mats
    0.46
     الحكوم
    0.45
     Grandma
    0.45
     grandma
    0.44
     Fargo
    0.44
     *
    0.43
     मैट्रिक्स
    0.43
     nomin
    0.42
    POSITIVE LOGITS
     aktivitas
    0.42
     воздействия
    0.42
    نش
    0.41
    ույ
    0.41
    ணை
    0.41
    处置
    0.41
    دست
    0.40
    ளிடம்
    0.40
    ру
    0.39
     weiteren
    0.39
    Activations Density 0.001%

    No Known Activations