© 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. 202876
    Prev
    Next
    INDEX
    Explanations

    Southern style

    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
     misfort
    0.48
    ガー
    0.47
     recycl
    0.43
     ingred
    0.43
    必要
    0.43
    Ingredients
    0.43
     recycling
    0.42
    県
    0.42
    marginLeft
    0.42
    durationType
    0.41
    POSITIVE LOGITS
     آی
    0.46
     Solaris
    0.46
     Bienvenido
    0.46
    avno
    0.45
    ுகளை
    0.45
    avelmente
    0.45
     obu
    0.44
    usak
    0.43
    ívne
    0.43
     എന്നാൽ
    0.43
    Activations Density 0.005%

    No Known Activations