© 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. 3467
    Prev
    Next
    INDEX
    Explanations

    liquid, fluids, and their states

    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
    ле
    1.44
    т
    1.34
    ی
    1.13
    та
    1.12
    Alumno
    1.10
    zantine
    1.09
    ⃣
    1.09
    Evento
    1.09
    किला
    1.08
    𝕟
    1.08
    POSITIVE LOGITS
     liquid
    1.48
     liquids
    1.31
     Liquid
    1.30
    liquid
    1.16
     Film
    1.12
    Liquid
    1.09
     sıvı
    1.09
     vapors
    1.02
     FILM
    1.02
     state
    1.01
    Activations Density 0.251%

    No Known Activations