© 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. 22232
    Prev
    Next
    INDEX
    Explanations

    lists of concepts or items

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

    listing with and or

    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
     "",
    0.51
    ],
    0.41
    ),
    0.40
     ],
    0.40
    /,
    0.39
     (),
    0.39
     cualquiera
    0.39
    なども
    0.39
     précédemment
    0.39
    するなど
    0.39
    POSITIVE LOGITS
    ጥረ
    0.47
    そして
    0.47
     przede
    0.46
     frankly
    0.46
     undeniably
    0.42
    לי
    0.42
    머니
    0.40
     importantly
    0.40
    Ă
    0.39
    vict
    0.38
    Activations Density 0.190%

    No Known Activations