© 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-IT
    3. 41-GEMMASCOPE-2-RES-16K
    4. 136
    Prev
    Next
    INDEX
    Explanations

    common word parts

    np_max-act-logits · gemini-2.5-flash-lite

    prefixes and short

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_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
    ग्वि
    0.57
     imassa
    0.55
     samoglas
    0.55
     yattha
    0.55
    clidean
    0.53
     punctato
    0.52
     combattre
    0.52
    󰡔
    0.52
    ួក
    0.52
    GBuf
    0.51
    POSITIVE LOGITS
     REST
    1.21
     FOR
    1.13
     RE
    1.13
     CON
    1.10
     IN
    1.08
     TO
    1.08
     PRO
    1.05
     AND
    1.05
     INTER
    1.05
     ON
    1.04
    Activations Density 0.864%

    No Known Activations