© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7327
    Prev
    Next
    INDEX
    Explanations

    contrasts and possibilities

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

    abstract concepts

    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_53_width_65k_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
     teritor
    0.42
    }\,\
    0.42
    当時の
    0.42
    )**
    0.41
     ব্যাপারটা
    0.41
     each
    0.40
     প্রতিষ্ঠানের
    0.40
    期の
    0.40
     },
    0.40
    时期
    0.39
    POSITIVE LOGITS
     possibilities
    0.88
     extremes
    0.88
     contrasts
    0.84
     contradictions
    0.82
     возможностей
    0.77
     dreams
    0.75
     posibilidades
    0.74
     possibilidades
    0.73
     sorrows
    0.72
     surprises
    0.71
    Activations Density 0.097%

    No Known Activations