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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 241693
    Prev
    Next
    INDEX
    Explanations

    concepts and processes

    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_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
    PatientR
    0.60
    那
    0.58
     नींव
    0.56
     სპ
    0.55
     लाइक
    0.55
     பேரா
    0.55
    रा
    0.55
    咦
    0.54
    窜
    0.54
     Tjiwarl
    0.54
    POSITIVE LOGITS
    ழிய
    0.58
    ార్థ
    0.55
     typing
    0.54
     renewal
    0.54
    ego
    0.53
     compart
    0.53
     closing
    0.53
     typed
    0.52
     Closing
    0.51
     renewed
    0.51
    Activations Density 0.001%

    No Known Activations