© 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. 14035
    Prev
    Next
    INDEX
    Explanations

    liking or preferring activities

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

    prefer or like

    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
     Possibly
    0.45
     posiblemente
    0.41
     possibly
    0.41
     Strugg
    0.40
     Goldstein
    0.40
    愍
    0.40
     தேவையான
    0.39
    始めて
    0.39
    嫄
    0.39
     Verstappen
    0.39
    POSITIVE LOGITS
     helst
    0.58
    が好き
    0.56
     нравится
    0.55
     surprises
    0.55
     préf
    0.54
     lieber
    0.53
     любят
    0.53
     люблю
    0.51
     preferably
    0.51
     একটু
    0.50
    Activations Density 0.135%

    No Known Activations