© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 127494
    Prev
    Next
    INDEX
    Explanations

    cost to collect

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

    North financed, Per oxide, Local traditions, friends know

    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
    Negative Logits
     deterministic
    0.43
     메서
    0.41
    elen
    0.40
    ణం
    0.39
    빤
    0.39
    стрее
    0.39
    мым
    0.38
    㧣
    0.38
    छोटे
    0.38
    ણમાં
    0.38
    POSITIVE LOGITS
     Natürlich
    0.48
     glassy
    0.48
     Algunos
    0.46
     sculpted
    0.46
     sayang
    0.46
    ęs
    0.45
    aceous
    0.44
     natürlich
    0.43
    ]=="
    0.43
     gratuito
    0.43
    Activations Density 0.000%

    No Known Activations