© 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. 174622
    Prev
    Next
    INDEX
    Explanations

    never guess, Group news, half metres

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

    phrases with ampersand

    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
    c
    0.55
    X
    0.51
    Y
    0.50
    V
    0.49
    t
    0.48
    maker
    0.47
    T
    0.46
    s
    0.45
    ON
    0.45
    of
    0.44
    POSITIVE LOGITS
    ולה
    0.51
    󰡔
    0.47
     felicidade
    0.46
     columnas
    0.45
     finalizar
    0.45
     mensagem
    0.44
     dizziness
    0.44
     पार्किंग
    0.44
     palavras
    0.44
     deceit
    0.44
    Activations Density 0.000%

    No Known Activations