© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 22800
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptions

    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
     quotas
    0.47
    z
    0.47
     expats
    0.46
    Do
    0.44
    DIY
    0.44
     ratio
    0.43
     maximum
    0.43
    POC
    0.43
    D
    0.43
     get
    0.42
    POSITIVE LOGITS
     adjectives
    0.65
     adjective
    0.64
    描写
    0.63
     description
    0.61
     descriptive
    0.60
    形容
    0.59
     Beschreibung
    0.58
     وصف
    0.57
    描述
    0.56
     describ
    0.55
    Activations Density 0.081%

    No Known Activations