© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136097
    Prev
    Next
    INDEX
    Explanations

    depending on

    np_acts-logits-general · gemini-2.5-flash-lite

    numbers and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ġ
    0.52
    ALI
    0.47
    يلي
    0.47
     Yıld
    0.45
    ığı
    0.44
     Deploy
    0.44
     অভিষ
    0.43
     bezpośred
    0.43
    iki
    0.42
    żą
    0.42
    POSITIVE LOGITS
     nostrils
    0.52
     pores
    0.51
     或
    0.50
     foaming
    0.50
     chemot
    0.49
    或
    0.49
     veins
    0.48
     tubs
    0.48
     ulcers
    0.47
     sore
    0.46
    Activations Density 0.001%

    No Known Activations