© 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-262K
    7. 7997
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by nouns

    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_262k_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
    ல்
    0.91
    я
    0.91
     r
    0.88
     U
    0.84
    ট
    0.82
     sheds
    0.80
    ка
    0.79
    ு
    0.77
     skyscraper
    0.77
    ist
    0.76
    POSITIVE LOGITS
    éristiques
    1.02
     aiutare
    0.95
     Gemeins
    0.93
    اویر
    0.93
    عبد
    0.91
     utilizza
    0.88
     negeri
    0.88
     být
    0.87
     dotycz
    0.86
     Entscheid
    0.86
    Activations Density 0.008%

    No Known Activations