© 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. 19898
    Prev
    Next
    INDEX
    Explanations

    forum discussion

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

    discussion and ideas

    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
    ⃖
    0.42
    getFullName
    0.41
     Inhibition
    0.41
     راستہ
    0.41
    між
    0.40
    Definition
    0.39
    صیٰ
    0.39
    ₂)
    0.39
    fullname
    0.39
    opatra
    0.39
    POSITIVE LOGITS
    讨论
    1.08
     forum
    1.05
     discussion
    0.99
     обсужда
    0.98
     форум
    0.98
    论坛
    0.96
     thread
    0.96
     forums
    0.96
     चर्चा
    0.95
    討論
    0.95
    Activations Density 0.108%

    No Known Activations