© 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. 143410
    Prev
    Next
    INDEX
    Explanations

    based upon, not overridden

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

    connecting words

    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
     Մ
    0.45
     ջ
    0.45
    残
    0.45
     август
    0.44
     いたし
    0.43
     നേരി
    0.43
     Прав
    0.43
     残
    0.42
     Πολ
    0.42
    bonding
    0.42
    POSITIVE LOGITS
     adição
    0.53
    一个是
    0.53
     addition
    0.51
     ponds
    0.45
     sone
    0.45
     vents
    0.44
    又是
    0.43
     possibilidades
    0.43
     lee
    0.43
     baths
    0.42
    Activations Density 0.002%

    No Known Activations