© 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
    3. 41-GEMMASCOPE-2-RES-65K
    4. 15256
    Prev
    Next
    INDEX
    Explanations

    raises

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_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
    lamide
    0.60
     ]];
    0.58
     गोपाल
    0.56
    资讯
    0.54
     (-
    0.52
     продви
    0.52
    一心
    0.52
    春
    0.51
    Socket
    0.51
    क्षित
    0.51
    POSITIVE LOGITS
     eyebrows
    1.63
     awareness
    1.38
    awareness
    1.29
     Awareness
    1.20
     eyebrow
    1.19
     alarms
    1.14
     funds
    1.05
     suspicions
    1.04
     flags
    0.99
     spirits
    0.98
    Activations Density 0.034%

    No Known Activations