© 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. 25710
    Prev
    Next
    INDEX
    Explanations

    commitment and sacrifice

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

    money as root of evil and temptation

    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
    NCE
    0.41
    間違い
    0.40
    ΗΣ
    0.39
    ophenyl
    0.38
     цик
    0.38
    вени
    0.37
     الداله
    0.37
    鑲
    0.37
    ENCE
    0.37
     tillbaka
    0.37
    POSITIVE LOGITS
     commitments
    0.44
    ऩे
    0.43
     commitment
    0.43
     Commitment
    0.42
     Trading
    0.42
     உயர்
    0.42
     relinquish
    0.42
     Selasa
    0.41
     إذ
    0.41
    ashita
    0.41
    Activations Density 0.030%

    No Known Activations