© 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. 199951
    Prev
    Next
    INDEX
    Explanations

    threats and failures

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

    linking specific categories of words

    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
    ɥ
    0.43
    onden
    0.42
     xr
    0.41
     weiterhin
    0.41
    ণ্ডে
    0.41
    ୀ
    0.40
    verso
    0.38
    ك
    0.38
    謝
    0.38
     vaguely
    0.38
    POSITIVE LOGITS
     failures
    0.44
     여기가
    0.44
     étages
    0.43
     Threats
    0.42
    failures
    0.42
     сообщи
    0.42
     etapas
    0.42
     thresholds
    0.41
    динку
    0.41
     वेळा
    0.41
    Activations Density 0.001%

    No Known Activations