© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 38627
    Prev
    Next
    INDEX
    Explanations

    hiring, contracted, commissioned, or retainer services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    V
    1.09
    '];
    1.02
    ak
    1.00
    K
    0.94
    }[
    0.93
     biển
    0.91
     الاعدادي
    0.89
     Saltar
    0.89
     Comunidad
    0.88
     Contents
    0.87
    POSITIVE LOGITS
    া
    0.96
     তাহলে
    0.91
     edile
    0.87
    normalize
    0.85
     normalize
    0.82
    ن
    0.80
    lere
    0.79
     admirably
    0.79
     stifle
    0.79
    therapeutic
    0.79
    Activations Density 0.066%

    No Known Activations