© 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. 202796
    Prev
    Next
    INDEX
    Explanations

    embryos, powders, Berry

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

    zombie lore lost

    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
    ες
    0.52
    ター
    0.51
    eref
    0.50
    ターン
    0.50
    𝔞
    0.49
    squeeze
    0.48
    ਾਸ
    0.47
    漆
    0.47
    ジャー
    0.46
    es
    0.46
    POSITIVE LOGITS
     Tomorrow
    0.49
     Btn
    0.49
     embryos
    0.49
     SeekBar
    0.49
     Futuristic
    0.48
     names
    0.48
     powders
    0.48
     Orch
    0.46
     Table
    0.46
     Berry
    0.46
    Activations Density 0.000%

    No Known Activations