© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 249227
    Prev
    Next
    INDEX
    Explanations

    expressing subjective states after "I feel"

    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
     Gefühl
    0.62
    n
    0.58
     Ende
    0.55
    in
    0.55
    感覚
    0.54
    ie
    0.51
     from
    0.50
     embossed
    0.50
     Ancient
    0.49
     Feeling
    0.49
    POSITIVE LOGITS
    此刻
    0.47
    总结
    0.45
    ことなく
    0.44
     podkre
    0.43
    会对
    0.42
     campañas
    0.41
    璃
    0.40
    emphas
    0.39
    强调
    0.38
     enfat
    0.38
    Activations Density 0.022%

    No Known Activations