© 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. 136805
    Prev
    Next
    INDEX
    Explanations

    travel and journeys

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

    describing travel style preferences

    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
    риа
    0.77
    ции
    0.76
    மாக
    0.71
    ங்களின்
    0.69
    يا
    0.68
    ب
    0.67
    ంగా
    0.64
    ರ
    0.64
    но
    0.63
    новой
    0.63
    POSITIVE LOGITS
    h
    0.92
    d
    0.81
     t
    0.80
    IN
    0.74
    z
    0.73
    AIS
    0.72
     Travelling
    0.68
     TRAVEL
    0.67
    I
    0.66
    GOLD
    0.66
    Activations Density 0.051%

    No Known Activations