© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3598
    Prev
    Next
    INDEX
    Explanations

    React

    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_16k_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
     эмне
    1.23
    為何
    1.20
     башка
    1.07
    берриз
    1.03
     Republike
    1.02
     potom
    1.00
    ﻒ
    1.00
    eksiyon
    0.99
    پلز
    0.99
     причины
    0.98
    POSITIVE LOGITS
     is
    1.01
     to
    0.97
     or
    0.97
     on
    0.93
     senses
    0.92
     can
    0.91
     of
    0.91
     for
    0.86
     excites
    0.85
    -
    0.84
    Activations Density 0.002%

    No Known Activations