© 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. 99839
    Prev
    Next
    INDEX
    Explanations

    making or protecting futures

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

    command substitution `$(...)`

    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
    チャンス
    0.43
     ecu
    0.43
    ini
    0.42
     scalar
    0.42
    </div>
    0.41
    以及
    0.41
    ++
    0.40
    그리고
    0.40
    ecu
    0.40
    POSITIVE LOGITS
     Firms
    0.56
     Pogis
    0.50
     Recommend
    0.48
     Ajust
    0.48
     Avoiding
    0.47
    𝐾
    0.47
    angerschaft
    0.46
     Batik
    0.46
    தய
    0.45
     केसांना
    0.45
    Activations Density 0.000%

    No Known Activations