© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111033
    Prev
    Next
    INDEX
    Explanations

    loss, data, license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    t
    0.53
    )?
    0.44
     sauvage
    0.44
     रू
    0.43
     abiotic
    0.43
     sneeze
    0.43
    😉
    0.43
    slateblue
    0.43
     vuole
    0.43
     deregulation
    0.42
    POSITIVE LOGITS
    ုပ်တို့
    0.46
    anging
    0.44
    ologically
    0.44
     अशोक
    0.43
    ices
    0.43
    oblasts
    0.42
    력을
    0.41
    审
    0.41
    ases
    0.41
    ika
    0.41
    Activations Density 0.000%

    No Known Activations