Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 26614
    Prev
    Next
    INDEX
    Explanations

    #!/usr/bin/env shebangs

    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
    rizioni
    0.41
    ﻕ
    0.39
     величина
    0.38
     invariant
    0.37
     mez
    0.37
     oligonucleotide
    0.37
     зре
    0.37
     vortices
    0.36
     cellar
    0.36
     চাপের
    0.36
    POSITIVE LOGITS
     বিনাম
    0.47
    awks
    0.43
     Toner
    0.42
    තු
    0.41
    simulation
    0.41
    ");
    0.41
    च्यू
    0.41
     Let
    0.40
     akun
    0.40
    নিজ
    0.40
    Activations Density 0.000%

    No Known Activations