© 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. 184590
    Prev
    Next
    INDEX
    Explanations

    left, down, below directions

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

    engaging with, still is, error within

    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
    ğın
    0.56
    ilibus
    0.46
    硋
    0.46
    澼
    0.46
    OC
    0.45
    acon
    0.45
    ilit
    0.44
    lii
    0.44
    亣
    0.44
    ylus
    0.43
    POSITIVE LOGITS
     betterment
    0.47
     transformative
    0.46
     competencies
    0.45
     touristic
    0.45
     transnational
    0.45
     flutter
    0.44
     trajectory
    0.44
    classical
    0.44
     infrastructural
    0.43
     cinematic
    0.43
    Activations Density 0.000%

    No Known Activations