© 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-16K
    7. 5724
    Prev
    Next
    INDEX
    Explanations

    countries and states

    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_16k_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
     άνθρω
    0.60
     جهانی
    0.50
     de
    0.47
    靠近
    0.45
    u
    0.45
     ilişkin
    0.45
    dataloader
    0.44
     সংশ
    0.44
     proche
    0.44
    <unused1048>
    0.44
    POSITIVE LOGITS
     thaliana
    0.58
    או
    0.56
    ру
    0.55
    ことを
    0.50
    PRO
    0.49
    は
    0.49
    ᖏ
    0.49
    يين
    0.49
    ᑉ
    0.47
     documentaries
    0.47
    Activations Density 0.388%

    No Known Activations